Animesh Garg

EDBT 2026 Demo / reviewers in the wild / expert

dblp:123/5728 · DBLP profile ↗

← Back

86ranked-venue papers

1as first author

55since 2021 · last 2025

0000-0003-0482-4296ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 82 · 55 since 2021Systems, architecture and hardware · 37 · 21 since 2021Graphics, computer vision, multimedia, augmented reality and games · 10 · 6 since 2021Applied, interdisciplinary, general and emerging computing · 2 · 1 first-author

Year	Publication	Venue	Position
2025	PWM: Policy Learning with Multi-Task World Models abstract Reinforcement Learning (RL) has made significant strides in complex tasks but struggles in multi-task settings with different embodiments. World model methods offer scalability by learning a simulation of the environment but often rely on inefficient gradient-free optimization methods for policy extraction. In contrast, gradient-based methods exhibit lower variance but fail to handle discontinuities. Our work reveals that well-regularized world models can generate smoother optimization landscapes than the actual dynamics, facilitating more effective first-order optimization. We introduce Policy learning with multi-task World Models (PWM), a novel model-based RL algorithm for continuous control. Initially, the world model is pre-trained on offline data, and then policies are extracted from it using first-order optimization in less than 10 minutes per task. PWM effectively solves tasks with up to 152 action dimensions and outperforms methods that use ground-truth dynamics. Additionally, PWM scales to an 80-task setting, achieving up to 27\% higher rewards than existing baselines without relying on costly online planning. Visualizations and code are available at [imgeorgiev.com/pwm](https://www.imgeorgiev.com/pwm/). Ignat Georgiev, Varun Giridhar, Nicklas Hansen 0001, Animesh Garg	ICLR	4
2025	EgoSim: Egocentric Exploration in Virtual Worlds with Multi-modal Conditioning abstract Recent advancements in video diffusion models have established a strong foundation for developing world models with practical applications. The next challenge lies in exploring how an agent can leverage these foundation models to understand, interact with, and plan within observed environments. This requires adding more controllability to the model, transforming it into a versatile game engine capable of dynamic manipulation and control. To address this, we investigated three key conditioning factors: camera, context frame, and text, identifying limitations in current model designs. Specifically, the fusion of camera embeddings with video features leads to camera control being influenced by those features. Additionally, while textual information compensates for necessary spatiotemporal structures, it often intrudes into already observed parts of the scene. To tackle these issues, we designed the Spacetime Epipolar Attention Layer, which ensures that egomotion generated by the model strictly aligns with the camera’s movement through rigid constraints. Moreover, we propose the CI2V-adapter, which uses camera information to better determine whether to prioritize textual or visual embeddings, thereby alleviating the issue of textual intrusion into observed areas. Through extensive experiments, we demonstrate that our new model EgoSim achieves excellent results on both the RealEstate and newly repurposed Epic-Field datasets. For more results, please refer to https://egosim.github.io/EgoSim/. Wei Yu 0001, Songheng Yin, Steve M. Easterbrook, Animesh Garg	ICLR	4
2025	RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations abstract Imitation learning in robotics faces significant challenges in generalization due to the complexity of robotic environments and the high cost of data collection. We introduce RoCoDA, a novel method that unifies the concepts of invariance, equivariance, and causality within a single framework to enhance data augmentation for imitation learning. RoCoDA leverages causal invariance by modifying task-irrelevant subsets of the environment state without affecting the policy's output. Simultaneously, we exploit SE (3) equivariance by applying rigid body transformations to object poses and adjusting corresponding actions to generate synthetic demonstrations. We validate RoCoDA through extensive experiments on five robotic manipulation tasks, demonstrating improvements in policy performance, generalization, and sample efficiency compared to state-of-the-art data augmentation methods. Our policies exhibit robust generalization to unseen object poses, textures, and the presence of distractors. Furthermore, we observe emergent behavior such as re-grasping, indicating policies trained with RoCoDA possess a deeper understanding of task dynamics. By leveraging invariance, equivariance, and causality, RoCoDA provides a principled approach to data augmentation in imitation learning, bridging the gap between geometric symmetries and causal reasoning. Project Page: https://rocoda.github.io Ezra Ameperosa, Jeremy A. Collins, Mrinal Jain, Animesh Garg	ICRA	4
2025	CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building abstract Intelligent and reliable task planning is a core capability for generalized robotics, which requires a descriptive domain representation that sufficiently models all object and state information for the scene. We present CLIMB, a continual learning framework for robot task planning that leverages foundation models and feedback from execution to guide the construction of domain models. CLIMB can build a model from a natural language description, learn non-obvious predicates while solving tasks, and store that information for future problems. We demonstrate the ability of CLIMB to improve performance in common planning environments compared to baseline methods. We also developed the BlocksWorld++ domain, a simulated environment with an easily usable real counterpart, together with a curriculum of tasks with progressing difficulty to evaluate continual learning. Code and additional details for this system can be found at https://plan-with-climb.github.io/. Walker Byrnes, Miroslav Bogdanovic, Avi Balakirsky, Stephen Balakirsky, Animesh Garg	ICRA	5
2025	SuFIA-BC: Generating High Quality Demonstration Data for Visuomotor Policy Learning in Surgical Subtasks abstract Behavior cloning facilitates the learning of dexterous manipulation skills, yet the complexity of surgical environments, the difficulty and expense of obtaining patient data, and robot calibration errors present unique challenges for surgical robot learning. We provide an enhanced surgical digital twin with photorealistic human anatomical organs, integrated into a comprehensive simulator designed to generate high-quality synthetic data to solve fundamental tasks in surgical autonomy. We present SuFIA-BC: visual Behavior Cloning policies for Surgical First Interactive Autonomy Assistants. We investigate visual observation spaces including multi-view cameras and 3D visual representations extracted from a single endoscopic camera view. Through systematic evaluation, we find that the diverse set of photorealistic surgical tasks introduced in this work enables a comprehensive evaluation of prospective behavior cloning models for the unique challenges posed by surgical environments. We observe that current state-of-the-art behavior cloning techniques struggle to solve the contact-rich and complex tasks evaluated in this work, regardless of their underlying perception or control architectures. These findings highlight the importance of customizing perception pipelines and control architectures, as well as curating larger-scale synthetic datasets that meet the specific demands of surgical tasks. Project website: orbit-surgical.github.io/sufia-bc/ Masoud Moghani, Nigel Nelson, Mohamed Ghanem, Andres Diaz-Pinto, Kush Hari, Mahdi Azizian, Kenneth Y. Goldberg, Sean Huver, Animesh Garg	ICRA	9
2025	ACGD: Visual Multitask Policy Learning with Asymmetric Critic Guided Distillation abstract We present Asymmetric Critic Guided Distillation, ACGD, a framework for learning multi-task dexterous manipulation policies that can manipulate articulated objects using images as input. ACGD is a scalable student-teacher distillation approach that utilizes behavior cloning to distill multiple expert policies into a single vision-based, multi-task student policy for dexterous manipulation. The expert policies are trained with traditional RL techniques with access to privileged state information of both the robot and the manipulated object, while the distilled student policy operates under realistic sensory constraints, specifically using only camera images and robot proprioception. During distillation, we use an expert-critic that provides action labels and value estimates to refine the student’s action sampling through a dual IL/RL objective. In the multi-task setting, we achieve this through an aggregate critic for different single-task experts. Our approach exhibits strong performance compared to a number of state-of-the-art imitation learning (IL) and reinforcement learning (RL) baselines. We evaluate across a variety of multi-task dexterous manipulation benchmarks including bimanual manipulation, single-hand object articulation tasks, and a tendon-actuated hand and achieves state-of-the-art performance with 10-15% improvement over the baseline algorithms. Visit our website for more details. Krishnan Srinivasan, Jie Xu 0028, Henry Ang, Eric Heiden, Dieter Fox, Jeannette Bohg, Animesh Garg	IROS	7
2024	Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation abstract Model-Free Reinforcement Learning (MFRL), leveraging the policy gradient theorem, has demonstrated considerable success in continuous control tasks. However, these approaches are plagued by high gradient variance due to zeroth-order gradient estimation, resulting in suboptimal policies. Conversely, First-Order Model-Based Reinforcement Learning (FO-MBRL) methods employing differentiable simulation provide gradients with reduced variance but are susceptible to sampling error in scenarios involving stiff dynamics, such as physical contact. This paper investigates the source of this error and introduces Adaptive Horizon Actor-Critic (AHAC), an FO-MBRL algorithm that reduces gradient error by adapting the model-based horizon to avoid stiff dynamics. Empirical findings reveal that AHAC outperforms MFRL baselines, attaining 40% more reward across a set of locomotion tasks and efficiently scaling to high-dimensional control environments with improved wall-clock-time efficiency. adaptive-horizon-actor-critic.github.io Ignat Georgiev, Krishnan Srinivasan, Jie Xu 0028, Eric Heiden, Animesh Garg	ICML	5
2024	Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration abstract Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin	ICRA	20
2024	Orbit-Surgical: An Open-Simulation Framework for Learning Surgical Augmented Dexterity abstract Physics-based simulations have accelerated progress in robot learning for driving, manipulation, and locomotion. Yet, a fast, accurate, and robust surgical simulation environment remains a challenge. In this paper, we present Orbit-Surgical, a physics-based surgical robot simulation framework with photorealistic rendering in NVIDIA Omniverse. We provide 14 benchmark surgical tasks for the da Vinci Research Kit (dVRK) and Smart Tissue Autonomous Robot (STAR) which represent common subtasks in surgical training. Orbit-Surgical leverages GPU parallelization to train reinforcement learning and imitation learning algorithms to facilitate study of robot learning to augment human surgical skills. Orbit-Surgical also facilitates realistic synthetic data generation for active perception tasks. We demonstrate Orbit-Surgical sim-to-real transfer of learned policies onto a physical dVRK robot.Project website: orbit-surgical.github.io Qinxi Yu, Masoud Moghani, Karthik Dharmarajan, Vincent Schorp, Will Panitch, Jingzhou Liu, Kush Hari, Mayank Mittal, Kenneth Y. Goldberg, Animesh Garg	ICRA	11
2024	HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors abstract Various heuristic objectives for modeling hand-object interaction have been proposed in past work. However, due to the lack of a cohesive framework, these objectives often possess a narrow scope of applicability and are limited by their efficiency or accuracy. In this paper, we propose HANDYPRIORS, a unified and general pipeline for pose estimation in human-object interaction scenes by leveraging recent advances in differentiable physics and rendering. Our approach employs rendering priors to align with input images and segmentation masks along with physics priors to mitigate penetration and relative-sliding across frames. Furthermore, we present two alternatives for hand and object pose estimation. The optimization-based pose estimation achieves higher accuracy, while the filtering-based tracking, which utilizes the differentiable priors as dynamics and observation models, executes faster. We demonstrate that HANDYPRIORS attains comparable or superior results in the pose estimation task, and that the differentiable physics module can predict contact information for pose refinement. We also show that our approach generalizes to perception tasks, including robotic hand manipulation and human-object pose estimation in the wild. Shutong Zhang, Yi-Ling Qiao, Guanglei Zhu, Eric Heiden, Dylan Turpin, Jingzhou Liu, Ming C. Lin, Miles Macklin, Animesh Garg	ICRA	9
2024	Fast Explicit-Input Assistance for Teleoperation in Clutter abstract The performance of prediction-based assistance for robot teleoperation degrades in unseen or goal-rich environments due to incorrect or quickly-changing intent inferences. Poor predictions can confuse operators or cause them to change their control input to implicitly signal their goal. We present a new assistance interface for robotic manipulation where an operator can explicitly communicate a manipulation goal by pointing the end-effector. The pointing target specifies a region for local pose generation and optimization, providing interactive control over grasp and placement pose candidates. We evaluate this explicit pointing interface against an implicit inference-based assistance scheme and an unassisted control condition in a within-subjects user study (N=20), where participants teleoperate a simulated robot to complete a multi-step singulation and stacking task in cluttered environments. We find that operators prefer the explicit interface, experience fewer pick failures and report lower cognitive workload. Our code is available at: github.com/NVlabs/fast-explicit-teleop. Nick Walker 0001, Xuning Yang, Animesh Garg, Maya Cakmak, Dieter Fox, Claudia Pérez-D'Arpino	IROS	3
2024	SuFIA: Language-Guided Augmented Dexterity for Robotic Surgical Assistants abstract In this work, we present SuFIA, the first framework for natural language-guided augmented dexterity for robotic surgical assistants. SuFIA incorporates the strong reasoning capabilities of large language models (LLMs) with perception modules to implement high-level planning and low-level control of a robot for surgical sub-task execution. This enables a learning-free approach to surgical augmented dexterity without any in-context examples or motion primitives. SuFIA uses a human-in-the-loop paradigm by restoring control to the surgeon in the case of insufficient information, mitigating unexpected errors for mission-critical tasks. We evaluate SuFIA on four surgical sub-tasks in a simulation environment and two sub-tasks on a physical surgical robotic platform in the lab, demonstrating its ability to perform common surgical sub-tasks through supervised autonomous operation under challenging physical and workspace conditions.Project website: orbit-surgical.github.io/sufia Masoud Moghani, Lars Doorenbos, Will Panitch, Sean Huver, Mahdi Azizian, Kenneth Y. Goldberg, Animesh Garg	IROS	7
2024	QueST: Self-Supervised Skill Abstractions for Learning Continuous Control abstract Generalization capabilities, or rather a lack thereof, is one of the most important unsolved problems in the field of robot learning, and while several large scale efforts have set out to tackle this problem, unsolved it remains. In this paper, we hypothesize that learning temporal action abstractions using latent variable models (LVMs), which learn to map data to a compressed latent space and back, is a promising direction towards low-level skills that can readily be used for new tasks. Although several works have attempted to show this, they have generally been limited by architectures that do not faithfully capture sharable representations. To address this we present Quantized Skill Transformer (QueST), which learns a larger and more flexible latent encoding that is more capable of modeling the breadth of low-level skills necessary for a variety of tasks. To make use of this extra flexibility, QueST imparts causal inductive bias from the action sequence data into the latent space, leading to more semantically useful and transferable representations. We compare to state-of-the-art imitation learning and LVM baselines and see that QueST’s architecture leads to strong performance on several multitask and few-shot learning benchmarks. Further results and videos are available at https://quest-model.github.io. Atharva Mete, Haotian Xue 0002, Albert Wilcox, Animesh Garg	NeurIPS	5
2024	Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning abstract A key challenge in offline reinforcement learning (RL) is how to ensure the learned offline policy is safe, especially in safety-critical domains. In this article, we focus on learning a distributional value function in offline RL and optimizing a worst-case criterion of returns. However, optimizing a distributional value function in offline RL can be hard, since the crossing quantile issue is serious, and the distribution shift problem needs to be addressed. To this end, we propose monotonic quantile network (MQN) with conservative quantile regression (CQR) for risk-averse policy learning. First, we propose an MQN to learn the distribution over returns with non-crossing guarantees of the quantiles. Then, we perform CQR by penalizing the quantile estimation for out-of-distribution (OOD) actions to address the distribution shift in offline RL. Finally, we learn a worst-case policy by optimizing the conditional value-at-risk (CVaR) of the distributional value function. Furthermore, we provide theoretical analysis of the fixed-point convergence in our method. We conduct experiments in both risk-neutral and risk-sensitive offline settings, and the results show that our method obtains safe and conservative behaviors in robotic locomotion tasks. Chenjia Bai, Ting Xiao 0002, Zhoufan Zhu, Lingxiao Wang 0003, Animesh Garg, Bin He 0003, Peng Liu 0008, Zhaoran Wang 0001	IEEE Trans. Neural Networks Learn. Syst.	6
2023	SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models Ziyi Wu 0002, Nikita Dvornik, Klaus Greff, Thomas Kipf, Animesh Garg	ICLR	5
2023	Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward Animesh Garg	ICLR	2
2023	nerf2nerf: Pairwise Registration of Neural Radiance Fields abstract We introduce a technique for pairwise registration of neural fields that extends classical optimization-based local registration (i.e. ICP) to operate on Neural Radiance Fields (NeRF)-neural 3D scene representations trained from collections of calibrated images. NeRF does not decompose illumination and color, so to make registration invariant to illumination, we introduce the concept of a “surface field” - a field distilled from a pre-trained NeRF model that measures the likelihood of a point being on the surface of an object. We then cast nerf2nerf registration as a robust optimization that iteratively seeks a rigid transformation that aligns the surface fields of the two scenes. We evaluate the effectiveness of our technique by introducing a dataset of pre-trained NeRF scenes - our synthetic scenes enable quantitative evaluations and comparisons to classical registration techniques, while our real scenes demonstrate the validity of our technique in real-world scenarios. Additional results available at: https://nerf2nerf.github.io Lily Goli, Daniel Rebain, Sara Sabour, Animesh Garg, Andrea Tagliasacchi	ICRA	4
2023	ProgPrompt: Generating Situated Robot Task Plans using Large Language Models abstract Task planning can require defining myriad domain knowledge about the world in which a robot needs to act. To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information. However, such methods either require enumerating all possible next steps for scoring, or generate free-form text that may contain actions not possible on a given robot in its current context. We present a programmatic LLM prompt structure that enables plan generation functional across situated environments, robot capabilities, and tasks. Our key insight is to prompt the LLM with program-like specifications of the available actions and objects in an environment, as well as with example programs that can be executed. We make concrete recommendations about prompt structure and generation constraints through ablation experiments, demonstrate state of the art success rates in VirtualHome household tasks, and deploy our method on a physical robot arm for tabletop tasks. Website at progprompt.github.io Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal 0001, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, Animesh Garg	ICRA	9
2023	Fast-Grasp'D: Dexterous Multi-finger Grasp Generation Through Differentiable Simulation abstract Multi-finger grasping relies on high quality training data, which is hard to obtain: human data is hard to transfer and synthetic data relies on simplifying assumptions that reduce grasp quality. By making grasp simulation differentiable, and contact dynamics amenable to gradient-based optimization, we accelerate the search for high-quality grasps with fewer limiting assumptions. We present Grasp'D-1M: a large-scale dataset for multi-finger robotic grasping, synthesized with Fast-Grasp'D, a novel differentiable grasping simulator. Grasp'D-1M contains one million training examples for three robotic hands (three, four and five-fingered), each with multimodal visual inputs (RGB+depth+segmentation, available in mono and stereo). Grasp synthesis with Fast-Grasp'D is 10x faster than GraspIt! [1] and 20x faster than the prior Grasp'D differentiable simulator [2]. Generated grasps are more stable and contact-rich than GraspIt! grasps, regardless of the distance threshold used for contact generation. We validate the usefulness of our dataset by retraining an existing vision-based grasping pipeline [3] on Grasp'D-1M, and showing a dramatic increase in model performance, predicting grasps with 30% more contact, a 33% higher epsilon metric, and 35% lower simulated displacement. Additional details at fast-graspd.github.io. Dylan Turpin, Tao Zhong 0003, Shutong Zhang, Guanglei Zhu, Eric Heiden, Miles Macklin, Stavros Tsogkas, Sven J. Dickinson, Animesh Garg	ICRA	9
2023	Self-Supervised Learning of Action Affordances as Interaction Modes abstract When humans perform a task with an articulated object, they interact with the object only in a handful of ways, while the space of all possible interactions is nearly endless. This is because humans have prior knowledge about what interactions are likely to be successful, i.e., to open a new door we first try the handle. While learning such priors without supervision is easy for humans, it is notoriously hard for machines. In this work, we tackle unsupervised learning of priors of useful interactions with articulated objects, which we call interaction modes. In contrast to the prior art, we use no supervision or privileged information; we only assume access to the depth sensor in the simulator to learn the interaction modes. More precisely, we define a successful interaction as the one changing the visual environment substantially and learn a generative model of such interactions, that can be conditioned on the desired goal state of the object. In our experiments, we show that our model covers most of the human interaction modes, outperforms existing state-of-the-art methods for affordance learning, and can generalize to objects never seen during training. Additionally, we show promising results in the goal-conditional setup, where our model can be quickly fine-tuned to perform a given task. We show in the experiments that such affordance learning predicts interaction which covers most modes of interaction for the querying articulated object and can be fine-tuned to a goal-conditional model. For supplementary: https://actaim.github.io/. Liquan Wang, Nikita Dvornik, Rafael Dubeau, Mayank Mittal, Animesh Garg	ICRA	5
2023	MVTrans: Multi-View Perception of Transparent Objects abstract Transparent object perception is a crucial skill for applications such as robot manipulation in household and laboratory settings. Existing methods utilize RGB-D or stereo inputs to handle a subset of perception tasks including depth and pose estimation. However transparent object perception remains to be an open problem. In this paper, we forgo the unreliable depth map from RGB-D sensors and extend the stereo based method. Our proposed method, MVTrans, is an end-to-end multi-view architecture with multiple perception capabilities, including depth estimation, segmentation, and pose estimation. Additionally, we establish a novel procedural photo-realistic dataset generation pipeline and create a large-scale transparent object detection dataset, Syn-TODD, which is suitable for training networks with all three modalities, RGB-D, stereo and multi-view RGB. https://ac-rad.github.io/MVTrans/ Yi Ru Wang, Yuchi Zhao, Haoping Xu, Sagi Eppel, Alán Aspuru-Guzik, Florian Shkurti, Animesh Garg	ICRA	7
2023	SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models abstract Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured representations that enable systematic generalization. Leveraging advanced architectures like Transformers, recent approaches have made significant progress in unsupervised object discovery. In addition, slot-based representations hold great potential for generative modeling, such as controllable image generation and object manipulation in image editing. However, current slot-based methods often produce blurry images and distorted objects, exhibiting poor generative modeling capabilities. In this paper, we focus on improving slot-to-image decoding, a crucial aspect for high-quality visual generation. We introduce SlotDiffusion -- an object-centric Latent Diffusion Model (LDM) designed for both image and video data. Thanks to the powerful modeling capacity of LDMs, SlotDiffusion surpasses previous slot models in unsupervised object segmentation and visual generation across six datasets. Furthermore, our learned object features can be utilized by existing object-centric dynamics models, improving video prediction quality and downstream temporal reasoning tasks. Finally, we demonstrate the scalability of SlotDiffusion to unconstrained real-world datasets such as PASCAL VOC and COCO, when integrated with self-supervised pre-trained image encoders. Ziyi Wu 0002, Wuyue Lu 0002, Igor Gilitschenski, Animesh Garg	NeurIPS	5
2023	Continuous-Time Fitted Value Iteration for Robust Policies abstract Solving the Hamilton-Jacobi-Bellman equation is important in many domains including control, robotics and economics. Especially for continuous control, solving this differential equation and its extension the Hamilton-Jacobi-Isaacs equation, is important as it yields the optimal policy that achieves the maximum reward on a give task. In the case of the Hamilton-Jacobi-Isaacs equation, which includes an adversary controlling the environment and minimizing the reward, the obtained policy is also robust to perturbations of the dynamics. In this paper we propose continuous fitted value iteration (cFVI) and robust fitted value iteration (rFVI). These algorithms leverage the non-linear control-affine dynamics and separable state and action reward of many continuous control problems to derive the optimal policy and optimal adversary in closed form. This analytic expression simplifies the differential equations and enables us to solve for the optimal value function using value iteration for continuous actions and states as well as the adversarial case. Notably, the resulting algorithms do not require discretization of states or actions. We apply the resulting algorithms to the Furuta pendulum and cartpole. We show that both algorithms obtain the optimal policy. The robustness Sim2Real experiments on the physical systems show that the policies successfully achieve the task in the real-world. When changing the masses of the pendulum, we observe that robust value iteration is more robust compared to deep reinforcement learning algorithm and the non-robust version of the algorithm. Videos of the experiments are shown at https://sites.google.com/view/rfvi. Michael Lutter, Boris Belousov, Shie Mannor, Dieter Fox, Animesh Garg, Jan Peters 0001	IEEE Trans. Pattern Anal. Mach. Intell.	5
2022	Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings abstract Policy gradient methods have been frequently applied to problems in control and reinforcement learning with great success, yet existing convergence analysis still relies on non-intuitive, impractical and often opaque conditions. In particular, existing rates are achieved in limited settings, under strict regularity conditions. In this work, we establish explicit convergence rates of policy gradient methods, extending the convergence regime to weakly smooth policy classes with L2 integrable gradient. We provide intuitive examples to illustrate the insight behind these new conditions. Notably, our analysis also shows that convergence rates are achievable for both the standard policy gradient and the natural policy gradient algorithms under these assumptions. Lastly we provide performance guarantees for the converged policies. Matthew Shunshi Zhang, Murat A. Erdogdu, Animesh Garg	AAAI	3
2022	Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors abstract Learning to autonomously assemble shapes is a crucial skill for many robotic applications. While the majority of existing part assembly methods focus on correctly posing semantic parts to recreate a whole object, we interpret assembly more literally: as mating geometric parts together to achieve a snug fit. By focusing on shape alignment rather than semantic cues, we can achieve across category generalization and scaling. In this paper, we introduce a novel task, pairwise 3D geometric shape mating, and propose Neural Shape Mating (NSM) to tackle this problem. Given point clouds of two object parts of an unknown category, NSM learns to reason about the fit of the two parts and predict a pair of 3D poses that tightly mate them together. In addition, we couple the training of NSM with an implicit shape reconstruction task, making NSM more robust to imperfect point cloud observations. To train NSM, we present a self-supervised data collection pipeline that generates pairwise shape mating data with ground truth by randomly cutting an object mesh into two parts, resulting in a dataset that consists of 200K shape mating pairs with numerous object meshes and diverse cut types. We train NSM on the collected dataset and compare it with several point cloud registration methods and one part assembly baseline approach. Extensive experimental results and ablation studies under various settings demonstrate the effectiveness of the proposed algorithm. Additional material is available at: neural-shape-mating.github.io. Yun-Chun Chen, Haoda Li, Dylan Turpin, Alec Jacobson, Animesh Garg	CVPR	5
2022	X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval abstract In text-video retrieval, the objective is to learn a cross-modal similarity function between a text and a video that ranks relevant text-video pairs higher than irrelevant pairs. However, videos inherently express a much wider gamut of information than texts. Instead, texts often capture sub-regions of entire videos and are most semantically similar to certain frames within videos. Therefore, for a given text, a retrieval model should focus on the text's most semantically similar video sub-regions to make a more relevant comparison. Yet, most existing works aggregate entire videos with-out directly considering text. Common text-agnostic ag-gregations schemes include mean-pooling or self-attention over the frames, but these are likely to encode misleading vi-sual information not described in the given text. To address this, we propose a cross-modal attention model called X-Pool that reasons between a text and the frames of a video. Our core mechanism is a scaled dot product attention for a text to attend to its most semantically similar frames. We then generate an aggregated video representation conditioned on the text's attention weights over the frames. We evaluate our method on three benchmark datasets of MSR-VTT, MSVD and LSMDC, achieving new state-of-the-art re-sults by up to 12% in relative improvement in Recall@ 1. Our findings thereby highlight the importance of joint text-video reasoning to extract important visual cues according to text. Full code and demo can be found at: layer6ai-labs.github.iolxpooll. Satya Krishna Gorti, Noël Vouitsis, Junwei Ma, Keyvan Golestan, Maksims Volkovs, Animesh Garg, Guangwei Yu	CVPR	6
2022	Modular Action Concept Grounding in Semantic Video Prediction abstract Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional pre-diction, which sidesteps the learning of interaction between agents and objects. We introduce the task of semantic action-conditional video prediction, which uses semantic action labels to describe those interactions and can be regarded as an inverse problem of action recognition. The challenge of this new task primarily lies in how to effectively inform the model of semantic action information. Inspired by the idea of Mixture of Experts, we embody each abstract label by a structured combination of various visual concept learn-ers and propose a novel video prediction model, Modular Action Concept Network (MAC). Our method is evaluated on two newly designed synthetic datasets, CLEVR-Building- Blocks and Sapien-Kitchen, and one real-world dataset called Tower-Creation. Extensive experiments demonstrate that MAC can correctly condition on given instructions and generate corresponding future frames without need of bounding boxes. We further show that the trained model can make out-of-distribution generalization, be quickly adapted to new object categories and exploit its learnt features for object detection, showing the progression towards higher-level cognitive abilities. More visualizations can be found at http://www.pair.toronto.edu/mac/. Wei Yu 0001, Songheng Yin, Steve M. Easterbrook, Animesh Garg	CVPR	5
2022	Grasp'D: Differentiable Contact-Rich Grasp Synthesis for Multi-Fingered Hands Dylan Turpin, Liquan Wang, Eric Heiden, Yun-Chun Chen, Miles Macklin, Stavros Tsogkas, Sven J. Dickinson, Animesh Garg	ECCV (6)	8
2022	Accelerated Policy Learning with Parallel Differentiable Simulation Jie Xu 0028, Viktor Makoviychuk, Yashraj Narang, Fabio Ramos 0001, Wojciech Matusik, Animesh Garg, Miles Macklin	ICLR	6
2022	Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning Chenjia Bai, Lingxiao Wang 0003, Zhuoran Yang, Zhihong Deng 0002, Animesh Garg, Peng Liu 0008, Zhaoran Wang 0001	ICLR	5
2022	Value Gradient weighted Model-Based Reinforcement Learning Claas Völcker, Victor Liao, Animesh Garg, Amir-massoud Farahmand	ICLR	3
2022	Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics abstract Offline reinforcement learning leverages large datasets to train policies without interactions with the environment. The learned policies may then be deployed in real-world settings where interactions are costly or dangerous. Current algorithms over-fit to the training dataset and as a consequence perform poorly when deployed to out-of-distribution generalizations of the environment. We aim to address these limitations by learning a Koopman latent representation which allows us to infer symmetries of the system’s underlying dynamic. The latter is then utilized to extend the otherwise static offline dataset during training; this constitutes a novel data augmentation framework which reflects the system’s dynamic and is thus to be interpreted as an exploration of the environments phase space. To obtain the symmetries we employ Koopman theory in which nonlinear dynamics are represented in terms of a linear operator acting on the space of measurement functions of the system. We provide novel theoretical results on the existence and nature of symmetries relevant for control systems such as reinforcement learning settings. Moreover, we empirically evaluate our method on several benchmark offline reinforcement learning tasks and datasets including D4RL, Metaworld and Robosuite and find that by using our framework we consistently improve the state-of-the-art of model-free Q-learning methods. Matthias Weissenbacher, Samarth Sinha, Animesh Garg, Yoshinobu Kawahara	ICML	3
2022	Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger abstract In-hand manipulation of objects is an important capability to enable robots to carry-out tasks which demand high levels of dexterity. This work presents a robot systems approach to learning dexterous manipulation tasks involving moving objects to arbitrary 6-DoF poses. We show empirical benefits, both in simulation and sim - to- real transfer, of using keypoint-based representations for object pose in policy observations and reward calculation to train a model-free reinforcement learning agent. By utilizing domain randomization strategies and large-scale training, we achieve a high success rate of 83 % on a real TriFinger system, with a single policy able to perform grasping, ungrasping, and finger gaiting in order to achieve arbitrary poses within the workspace. We demonstrate that our policy can generalise to unseen objects, and success rates can be further improved through finetuning. With the aim of assisting further research in learning in-hand manipulation, we provide a detailed exposition of our system and make the codebase of our system available, along with checkpoints trained on billions of steps of experience, at https://s2r2-ig.github.io Arthur Allshire, Mayank Mittal, Varun Lodaya, Viktor Makoviychuk, Denys Makoviichuk, Felix Widmaier, Manuel Wüthrich, Stefan Bauer, Ankur Handa, Animesh Garg	IROS	10
2022	Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation abstract A kitchen assistant needs to operate human-scale objects, such as cabinets and ovens, in unmapped environments with dynamic obstacles. Autonomous interactions in such environments require integrating dexterous manipulation and fluid mobility. While mobile manipulators in different form factors provide an extended workspace, their real-world adoption has been limited. Executing a high-level task for general objects requires a perceptual understanding of the object as well as adaptive whole-body control among dynamic obstacles. In this paper, we propose a two-stage architecture for autonomous interaction with large articulated objects in unknown environments. The first stage, object-centric planner, only focuses on the object to provide an action-conditional sequence of states for manipulation using RGB-D data. The second stage, agent-centric planner, formulates the whole-body motion control as an optimal control problem that ensures safe tracking of the generated plan, even in scenes with moving obstacles. We show that the proposed pipeline can handle complex static and dynamic kitchen settings for both wheel-based and legged mobile manipulators. Compared to other agent-centric planners, our proposed planner achieves a higher success rate and a lower execution time. We also perform hardware tests on a legged mobile manipulator to interact with various articulated objects in a kitchen. For additional material, please check: www.pair.toronto.edularticulated-mm/. Mayank Mittal, David Hoeller, Farbod Farshidian, Marco Hutter 0001, Animesh Garg	IROS	5
2022	MoCoDA: Model-based Counterfactual Data Augmentation abstract The number of states in a dynamic process is exponential in the number of objects, making reinforcement learning (RL) difficult in complex, multi-object domains. For agents to scale to the real world, they will need to react to and reason about unseen combinations of objects. We argue that the ability to recognize and use local factorization in transition dynamics is a key element in unlocking the power of multi-object reasoning. To this end, we show that (1) known local structure in the environment transitions is sufficient for an exponential reduction in the sample complexity of training a dynamics model, and (2) a locally factored dynamics model provably generalizes out-of-distribution to unseen states and actions. Knowing the local structure also allows us to predict which unseen states and actions this dynamics model will generalize to. We propose to leverage these observations in a novel Model-based Counterfactual Data Augmentation (MoCoDA) framework. MoCoDA applies a learned locally factored dynamics model to an augmented distribution of states and actions to generate counterfactual transitions for RL. MoCoDA works with a broader set of local structures than prior work and allows for direct control over the augmented training distribution. We show that MoCoDA enables RL agents to learn policies that generalize to unseen states and actions. We use MoCoDA to train an offline RL agent to solve an out-of-distribution robotics manipulation task on which standard offline RL algorithms fail. Silviu Pitis, Elliot Creager, Ajay Mandlekar, Animesh Garg	NeurIPS	4
2022	Breaking Bad: A Dataset for Geometric Fracture and Reassembly abstract We introduce Breaking Bad, a large-scale dataset of fractured objects. Our dataset consists of over one million fractured objects simulated from ten thousand base models. The fracture simulation is powered by a recent physically based algorithm that efficiently generates a variety of fracture modes of an object. Existing shape assembly datasets decompose objects according to semantically meaningful parts, effectively modeling the construction process. In contrast, Breaking Bad models the destruction process of how a geometric object naturally breaks into fragments. Our dataset serves as a benchmark that enables the study of fractured object reassembly and presents new challenges for geometric shape understanding. We analyze our dataset with several geometry measurements and benchmark three state-of-the-art shape assembly deep learning methods under various settings. Extensive experimental results demonstrate the difficulty of our dataset, calling on future research in model designs specifically for the geometric shape assembly task. We host our dataset at https://breaking-bad-dataset.github.io/. Silvia Sellán, Yun-Chun Chen, Ziyi Wu 0002, Animesh Garg, Alec Jacobson	NeurIPS	4
2022	SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments abstract Traditional biological and pharmaceutical manufacturing plants are controlled by human workers or pre-defined thresholds. Modernized factories have advanced process control algorithms such as model predictive control (MPC). However, there is little exploration of applying deep reinforcement learning to control manufacturing plants. One of the reasons is the lack of high fidelity simulations and standard APIs for benchmarking. To bridge this gap, we develop an easy-to-use library that includes five high-fidelity simulation environments: BeerFMTEnv, ReactorEnv, AtropineEnv, PenSimEnv and mAbEnv, which cover a wide range of manufacturing processes. We build these environments on published dynamics models. Furthermore, we benchmark online and offline, model-based and model-free reinforcement learning algorithms for comparisons of follow-up research. Mohan Zhang, Xiaozhou Wang, Benjamin Decardi-Nelson, Song Bo, An Zhang 0007, Jinfeng Liu 0001, Sile Tao, Jiayi Cheng, Xiaohong Liu 0001, Dengdeng Yu, Matthew Poon, Animesh Garg	NeurIPS	12
2022	GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model Zhaoming Xie, Xingye Da, Buck Babich, Animesh Garg, Michiel van de Panne	WAFR	4
2022	Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos abstract Unsupervised landmark learning is the task of learning semantic keypoint-like representations without the use of expensive input keypoint annotations. A popular approach is to factorize an image into a pose and appearance data stream, then to reconstruct the image from the factorized components. The pose representation should capture a set of consistent and tightly localized landmarks in order to facilitate reconstruction of the input image. Ultimately, we wish for our learned landmarks to focus on the foreground object of interest. However, the reconstruction task of the entire image forces the model to allocate landmarks to model the background. Using a motion-based foreground assumption, this work explores the effects of factorizing the reconstruction task into separate foreground and background reconstructions in an unsupervised way, allowing the model to condition only the foreground reconstruction on the unsupervised landmarks. Our experiments demonstrate that the proposed factorization results in landmarks that are focused on the foreground object of interest when measured against ground-truth foreground masks. Furthermore, the rendered background quality is also improved as ill-suited landmarks are no longer forced to model this content. We demonstrate this improvement via improved image fidelity in a video-prediction task. Code is available at https://github.com/NVIDIA/UnsupervisedLandmarkLearning. Aysegul Dundar, Kevin J. Shih, Animesh Garg, Robert Pottorf, Andrew Tao, Bryan Catanzaro	IEEE Trans. Pattern Anal. Mach. Intell.	3
2021	DIBS: Diversity Inducing Information Bottleneck in Model Ensembles abstract Although deep learning models have achieved state-of-the art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research. Bayesian approaches including Bayesian Neural Nets (BNNs) do not scale well to modern computer vision tasks, as they are difficult to train, and have poor generalization under dataset-shift. This motivates the need for effective ensembles which can generalize and give reliable uncertainty estimates. In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning the stochastic latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. We evaluate our method on benchmark datasets: MNIST, CIFAR100, TinyImageNet and MIT Places 2, and compared to the most competitive baselines show significant improvements in classification accuracy, under a shift in the data distribution and in out-of-distribution detection. over 10% relative improvement in classification accuracy, over 5% relative improvement in generalizing under dataset shift, and over 5% better predictive uncertainty estimation as inferred by efficient out-of-distribution (OOD) detection. Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti	AAAI	5
2021	Conservative Safety Critics for Exploration Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg	ICLR	6
2021	C-Learning: Horizon-Aware Cumulative Accessibility Estimation Panteha Naderian, Gabriel Loaiza-Ganem, Harry J. Braviner, Anthony L. Caterini, Jesse C. Cresswell, Animesh Garg	ICLR	7
2021	Latent Skill Planning for Exploration and Transfer Kevin Xie, Homanga Bharadhwaj, Danijar Hafner, Animesh Garg, Florian Shkurti	ICLR	4
2021	Principled Exploration via Optimistic Bootstrapping and Backward Induction abstract One principled approach for provably efficient exploration is incorporating the upper confidence bound (UCB) into the value function as a bonus. However, UCB is specified to deal with linear and tabular settings and is incompatible with Deep Reinforcement Learning (DRL). In this paper, we propose a principled exploration method for DRL through Optimistic Bootstrapping and Backward Induction (OB2I). OB2I constructs a general-purpose UCB-bonus through non-parametric bootstrap in DRL. The UCB-bonus estimates the epistemic uncertainty of state-action pairs for optimistic exploration. We build theoretical connections between the proposed UCB-bonus and the LSVI-UCB in linear setting. We propagate future uncertainty in a time-consistent manner through episodic backward update, which exploits the theoretical advantage and empirically improves the sample-efficiency. Our experiments in MNIST maze and Atari suit suggest that OB2I outperforms several state-of-the-art exploration approaches. Chenjia Bai, Lingxiao Wang 0003, Lei Han 0001, Jianye Hao, Animesh Garg, Peng Liu 0008, Zhaoran Wang 0001	ICML	5
2021	Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition abstract In real-world multi-agent systems, agents with different capabilities may join or leave without altering the team’s overarching goals. Coordinating teams with such dynamic composition is challenging: the optimal team strategy varies with the composition. We propose COPA, a coach-player framework to tackle this problem. We assume the coach has a global view of the environment and coordinates the players, who only have partial views, by distributing individual strategies. Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players. We validate our methods on a resource collection task, a rescue game, and the StarCraft micromanagement tasks. We demonstrate zero-shot generalization to new team compositions. Our method achieves comparable or better performance than the setting where all players have a full view of the environment. Moreover, we see that the performance remains high even when the coach communicates as little as 13% of the time using the adaptive communication strategy. Bo Liu 0042, Qiang Liu 0001, Peter Stone 0001, Animesh Garg, Yuke Zhu, Anima Anandkumar	ICML	4
2021	Value Iteration in Continuous Actions, States and Time abstract Classical value iteration approaches are not applicable to environments with continuous states and actions. For such environments the states and actions must be discretized, which leads to an exponential increase in computational complexity. In this paper, we propose continuous fitted value iteration (cFVI). This algorithm enables dynamic programming for continuous states and actions with a known dynamics model. Exploiting the continuous time formulation, the optimal policy can be derived for non-linear control-affine dynamics. This closed-form solution enables the efficient extension of value iteration to continuous environments. We show in non-linear control experiments that the dynamic programming solution obtains the same quantitative performance as deep reinforcement learning methods in simulation but excels when transferred to the physical system.The policy obtained by cFVI is more robust to changes in the dynamics despite using only a deterministic model and without explicitly incorporating robustness in the optimization Michael Lutter, Shie Mannor, Jan Peters 0001, Dieter Fox, Animesh Garg	ICML	5
2021	Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning abstract Reinforcement Learning in large action spaces is a challenging problem. This is especially true for cooperative multi-agent reinforcement learning (MARL), which often requires tractable learning while respecting various constraints like communication budget and information about other agents. In this work, we focus on the fundamental hurdle affecting both value-based and policy-gradient approaches: an exponential blowup of the action space with the number of agents. For value-based methods, it poses challenges in accurately representing the optimal value function for value-based methods, thus inducing suboptimality. For policy gradient methods, it renders the critic ineffective and exacerbates the problem of the lagging critic. We show that from a learning theory perspective, both problems can be addressed by accurately representing the associated action-value function with a low-complexity hypothesis class. This requires accurately modelling the agent interactions in a sample efficient way. To this end, we propose a novel tensorised formulation of the Bellman equation. This gives rise to our method Tesseract, which utilises the view of Q-function seen as a tensor where the modes correspond to action spaces of different agents. Algorithms derived from Tesseract decompose the Q-tensor across the agents and utilise low-rank tensor approximations to model the agent interactions relevant to the task. We provide PAC analysis for Tesseract based algorithms and highlight their relevance to the class of rich observation MDPs. Empirical results in different domains confirm the gains in sample efficiency using Tesseract as supported by the theory. Anuj Mahajan, Mikayel Samvelyan, Viktor Makoviychuk, Animesh Garg, Jean Kossaifi, Shimon Whiteson, Yuke Zhu, Anima Anandkumar	ICML	5
2021	LASER: Learning a Latent Action Space for Efficient Reinforcement Learning abstract The process of learning a manipulation task depends strongly on the action space used for exploration: posed in the incorrect action space, solving a task with reinforcement learning can be drastically inefficient. Additionally, similar tasks or instances of the same task family impose latent manifold constraints on the most effective action space: the task family can be best solved with actions in a manifold of the entire action space of the robot. Combining these insights we present LASER, a method to learn latent action spaces for efficient reinforcement learning. LASER factorizes the learning problem into two sub-problems, namely action space learning and policy learning in the new action space. It leverages data from similar manipulation task instances, either from an offline expert or online during policy learning, and learns from these trajectories a mapping from the original to a latent action space. LASER is trained as a variational encoder-decoder model to map raw actions into a disentangled latent action space while maintaining action reconstruction and latent space dynamic consistency. We evaluate LASER on two contact-rich robotic tasks in simulation, and analyze the benefit of policy learning in the generated latent action space. We show improved sample efficiency compared to the original action space from better alignment of the action space to the task space, as we observe with visualizations of the learned action space manifold. Additional details: pair.toronto.edu/laser Arthur Allshire, Roberto Martin Martin, Charles Lin, Shawn Manuel, Silvio Savarese, Animesh Garg	ICRA	6
2021	LEAF: Latent Exploration Along the Frontier abstract Self-supervised goal proposal and reaching is a key component for exploration and efficient policy learning algorithms. Such a self-supervised approach without access to any oracle goal sampling distribution requires deep exploration and commitment so that long horizon plans can be efficiently discovered. In this paper, we propose an exploration framework, which learns a dynamics-aware manifold of reachable states. For a goal, our proposed method deterministically visits a state at the current frontier of reachable states (commit- ment/reaching) and then stochastically explores to reach the goal (exploration). This allocates exploration budget near the frontier of the reachable region instead of its interior. We target the challenging problem of policy learning from initial and goal states specified as images, and do not assume any access to the underlying ground-truth states of the robot and the environment. To keep track of reachable latent states, we propose a distance-conditioned reachability network that is trained to infer whether one state is reachable from another within the specified latent space distance. Given an initial state, we obtain a frontier of reachable states from that state. By incorporating a curriculum for sampling easier goals (closer to the start state) before more difficult goals, we demonstrate that the proposed self-supervised exploration algorithm, superior performance compared to existing baselines on a set of challenging robotic environments. https://sites.google.com/view/leaf-exploration Homanga Bharadhwaj, Animesh Garg, Florian Shkurti	ICRA	2
2021	Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects abstract Evolution in nature illustrates that the creatures’ biological structure and their sensorimotor skills adapt to the environmental changes for survival. Likewise, the ability to morph and acquire new skills can facilitate an embodied agent to solve tasks of varying complexities. In this work, we introduce a data-driven approach where effective hand designs naturally emerge for the purpose of grasping diverse objects. Jointly optimizing morphology and control imposes computational challenges since it requires constant evaluation of a black-box function that measures the performance of a combination of embodiment and behavior. We develop a novel Bayesian Optimization algorithm that efficiently co-designs the morphology and grasping skills through learned latent-space representations. We design the grasping tasks based on a taxonomy of human grasp types: power grasp, pinch grasp, and lateral grasp. Through experimentation and comparative study, we demonstrate that our approach discovers robust and cost-efficient hand morphologies for grasping novel objects. Additional videos and results at https://xinleipan.github.io/emergent_morphology Xinlei Pan, Animesh Garg, Anima Anandkumar, Yuke Zhu	ICRA	2
2021	Dynamics Randomization Revisited: A Case Study for Quadrupedal Locomotion abstract Understanding the gap between simulation and reality is critical for reinforcement learning with legged robots, which are largely trained in simulation. However, recent work has resulted in sometimes conflicting conclusions with regard to which factors are important for success, including the role of dynamics randomization. In this paper, we aim to provide clarity and understanding on the role of dynamics randomization in learning robust locomotion policies for the Laikago quadruped robot. Surprisingly, in contrast to prior work with the same robot model, we find that direct sim-to-real transfer is possible without dynamics randomization or on-robot adaptation schemes. We conduct extensive ablation studies in a sim-to-sim setting to understand the key issues underlying successful policy transfer, including other design decisions that can impact policy robustness. We further ground our conclusions via sim-to-real experiments with various gaits, speeds, and stepping frequencies. Additional Details: pair.toronto.edu/understanding-dr/ Zhaoming Xie, Xingye Da, Michiel van de Panne, Buck Babich, Animesh Garg	ICRA	5
2021	Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos abstract Learning from visual data opens the potential to accrue a large range of manipulation behaviors by leveraging human demonstrations without specifying each of them mathe-matically, but rather through natural task specification. In this paper, we present Learning by Watching (LbW), an algorithmic framework for policy learning through imitation from a single video specifying the task. The key insights of our method are two-fold. First, since the human arms may not have the same morphology as robot arms, our framework learns unsupervised human to robot translation to overcome the morphology mis-match issue. Second, to capture the details in salient regions that are crucial for learning state representations, our model performs unsupervised keypoint detection on the translated robot videos. The detected keypoints form a structured representation that contains semantically meaningful information and can be used directly for computing reward and policy learning. We evaluate the effectiveness of our LbW framework on five robot manipulation tasks, including reaching, pushing, sliding, coffee making, and drawer closing. Extensive experimental evaluations demonstrate that our method performs favorably against the state-of-the-art approaches. More results and analysis are available at pair.toronto.edu/lbw-kp/. Haoyu Xiong, Quanzhou Li, Yun-Chun Chen, Homanga Bharadhwaj, Samarth Sinha, Animesh Garg	IROS	6
2021	Dynamic Bottleneck for Robust Self-Supervised Exploration abstract Exploration methods based on pseudo-count of transitions or curiosity of dynamics have achieved promising results in solving reinforcement learning with sparse rewards. However, such methods are usually sensitive to environmental dynamics-irrelevant information, e.g., white-noise. To handle such dynamics-irrelevant information, we propose a Dynamic Bottleneck (DB) model, which attains a dynamics-relevant representation based on the information-bottleneck principle. Based on the DB model, we further propose DB-bonus, which encourages the agent to explore state-action pairs with high information gain. We establish theoretical connections between the proposed DB-bonus, the upper confidence bound (UCB) for linear case, and the visiting count for tabular case. We evaluate the proposed method on Atari suits with dynamics-irrelevant noises. Our experiments show that exploration with DB bonus outperforms several state-of-the-art exploration methods in noisy environments. Chenjia Bai, Lingxiao Wang 0003, Lei Han 0001, Animesh Garg, Jianye Hao, Peng Liu 0008, Zhaoran Wang 0001	NeurIPS	4
2021	Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers abstract In this work, we consider the problem of sequence-to-sequence alignment for signals containing outliers. Assuming the absence of outliers, the standard Dynamic Time Warping (DTW) algorithm efficiently computes the optimal alignment between two (generally) variable-length sequences. While DTW is robust to temporal shifts and dilations of the signal, it fails to align sequences in a meaningful way in the presence of outliers that can be arbitrarily interspersed in the sequences. To address this problem, we introduce Drop-DTW, a novel algorithm that aligns the common signal between the sequences while automatically dropping the outlier elements from the matching. The entire procedure is implemented as a single dynamic program that is efficient and fully differentiable. In our experiments, we show that Drop-DTW is a robust similarity measure for sequence retrieval and demonstrate its effectiveness as a training loss on diverse applications. With Drop-DTW, we address temporal step localization on instructional videos, representation learning from noisy videos, and cross-modal representation learning for audio-visual retrieval and localization. In all applications, we take a weakly- or unsupervised approach and demonstrate state-of-the-art results under these settings. Nikita Dvornik, Isma Hadji, Konstantinos G. Derpanis, Animesh Garg, Allan Douglas Jepson	NeurIPS	4
2021	Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions abstract Effective control and prediction of dynamical systems require appropriate handling of continuous-time and discrete, event-triggered processes. Stochastic hybrid systems (SHSs), common across engineering domains, provide a formalism for dynamical systems subject to discrete, possibly stochastic, state jumps and multi-modal continuous-time flows. Despite the versatility and importance of SHSs across applications, a general procedure for the explicit learning of both discrete events and multi-mode continuous dynamics remains an open problem. This work introduces Neural Hybrid Automata (NHAs), a recipe for learning SHS dynamics without a priori knowledge on the number, mode parameters, and inter-modal transition dynamics. NHAs provide a systematic inference method based on normalizing flows, neural differential equations, and self-supervision. We showcase NHAs on several tasks, including mode recovery and flow learning in systems with stochastic transitions, and end-to-end learning of hierarchical robot controllers. Michael Poli, Stefano Massaroli, Luca Scimeca, Sanghyuk Chun, Seong Joon Oh, Atsushi Yamashita, Hajime Asama, Jinkyoo Park, Animesh Garg	NeurIPS	9
2020	Angular Visual Hardness abstract Recent convolutional neural networks (CNNs) have led to impressive performance but often suffer from poor calibration. They tend to be overconfident, with the model confidence not always reflecting the underlying true ambiguity and hardness. In this paper, we propose angular visual hardness (AVH), a score given by the normalized angular distance between the sample feature embedding and the target classifier to measure sample hardness. We validate this score with an in-depth and extensive scientific study, and observe that CNN models with the highest accuracy also have the best AVH scores. This agrees with an earlier finding that state-of-art models improve on the classification of harder examples. We observe that the training dynamics of AVH is vastly different compared to the training loss. Specifically, AVH quickly reaches a plateau for all samples even though the training loss keeps improving. This suggests the need for designing better loss functions that can target harder examples more effectively. We also find that AVH has a statistically significant correlation with human visual hardness. Finally, we demonstrate the benefit of AVH to a variety of applications such as self-training for domain adaptation and domain generalization. Beidi Chen, Weiyang Liu, Zhiding Yu, Jan Kautz, Anshumali Shrivastava, Animesh Garg, Anima Anandkumar	ICML	6
2020	Semi-Supervised StyleGAN for Disentanglement Learning abstract Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, primarily focusing on learning disentangled representations, and non-identifiability due to the unsupervised setting. To alleviate these limitations, we design new architectures and loss functions based on StyleGAN (Karras et al., 2019), for semi-supervised high-resolution disentanglement learning. We create two complex high-resolution synthetic datasets for systematic testing. We investigate the impact of limited supervision and find that using only 0.25% 2.5% of labeled data is sufficient for good disentanglement on both synthetic and real datasets. We propose new metrics to quantify generator controllability, and observe there may exist a crucial trade-off between disentangled representation learning and controllable generation. We also consider semantic fine-grained image editing to achieve better generalization to unseen images. Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debnath, Anjul Patney, Ankit B. Patel, Anima Anandkumar	ICML	3
2020	Motion Reasoning for Goal-Based Imitation Learning abstract We address goal-based imitation learning, where the aim is to output the symbolic goal from a third-person video demonstration. This enables the robot to plan for execution and reproduce the same goal in a completely different environment. The key challenge is that the goal of a video demonstration is often ambiguous at the level of semantic actions. The human demonstrators might unintentionally achieve certain subgoals in the demonstrations with their actions. Our main contribution is to propose a motion reasoning framework that combines task and motion planning to disambiguate the true intention of the demonstrator in the video demonstration. This allows us to recognize the goals that cannot be disambiguated by previous action-based approaches. We evaluate our approach on a new dataset of 96 video demonstrations in a mockup kitchen environment. We show that our motion reasoning plays an important role in recognizing the actual goal of the demonstrator and improves the success rate by over 20%. We further show that by using the automatically inferred goal from the video demonstration, our robot is able to reproduce the same task in a real kitchen environment. De-An Huang, Yu-Wei Chao, Chris Paxton 0001, Xinke Deng, Li Fei-Fei 0001, Juan Carlos Niebles, Animesh Garg, Dieter Fox	ICRA	7
2020	Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning abstract Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. On the other hand, reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sampleinefficient and brittle. In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline, while requiring minimal interactions with the environment. This is achieved by leveraging uncertainty estimates to divide the space in regions where the given model-based policy is reliable, and regions where it may have flaws or not be well defined. In these uncertain regions, we show that a locally learned-policy can be used directly with raw sensory inputs. We test our algorithm, Guided Uncertainty-Aware Policy Optimization (GUAPO), on a real-world robot performing peg insertion. Videos are available at: https://sites.google.com/view/guapo-rl. Michelle A. Lee, Carlos Florensa, Jonathan Tremblay, Nathan D. Ratliff, Animesh Garg, Fabio Ramos 0001, Dieter Fox	ICRA	5
2020	Controlling Assistive Robots with Learned Latent Actions abstract Assistive robotic arms enable users with physical disabilities to perform everyday tasks without relying on a caregiver. Unfortunately, the very dexterity that makes these arms useful also makes them challenging to teleoperate: the robot has more degrees-of-freedom than the human can directly coordinate with a handheld joystick. Our insight is that we can make assistive robots easier for humans to control by leveraging latent actions. Latent actions provide a lowdimensional embedding of high-dimensional robot behavior: for example, one latent dimension might guide the assistive arm along a pouring motion. In this paper, we design a teleoperation algorithm for assistive robots that learns latent actions from task demonstrations. We formulate the controllability, consistency, and scaling properties that user-friendly latent actions should have, and evaluate how different lowdimensional embeddings capture these properties. Finally, we conduct two user studies on a robotic arm to compare our latent action approach to both state-of-the-art shared autonomy baselines and a teleoperation strategy currently used by assistive arms. Participants completed assistive eating and cooking tasks more efficiently when leveraging our latent actions, and also subjectively reported that latent actions made the task easier to perform. The video accompanying this paper can be found at: https://youtu.be/wjnhrzugBj4. Dylan P. Losey, Krishnan Srinivasan, Ajay Mandlekar, Animesh Garg, Dorsa Sadigh	ICRA	4
2020	IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data abstract Learning from offline task demonstrations is a problem of great interest in robotics. For simple short-horizon manipulation tasks with modest variation in task instances, offline learning from a small set of demonstrations can produce controllers that successfully solve the task. However, leveraging a fixed batch of data can be problematic for larger datasets and longer-horizon tasks with greater variations. The data can exhibit substantial diversity and consist of suboptimal solution approaches. In this paper, we propose Implicit Reinforcement without Interaction at Scale (IRIS), a novel framework for learning from large-scale demonstration datasets. IRIS factorizes the control problem into a goal-conditioned low-level controller that imitates short demonstration sequences and a high-level goal selection mechanism that sets goals for the low-level and selectively combines parts of suboptimal solutions leading to more successful task completions. We evaluate IRIS across three datasets, including the RoboTurk Cans dataset collected by humans via crowdsourcing, and show that performant policies can be learned from purely offline learning. Additional results at https://sites.google.com/stanford.edu/iris/. Ajay Mandlekar, Fabio Ramos 0001, Byron Boots, Silvio Savarese, Li Fei-Fei 0001, Animesh Garg, Dieter Fox	ICRA	6
2020	Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter abstract When searching for objects in cluttered environments, it is often necessary to perform complex interactions in order to move occluding objects out of the way and fully reveal the object of interest and make it graspable. Due to the complexity of the physics involved and the lack of accurate models of the clutter, planning and controlling precise predefined interactions with accurate outcome is extremely hard, when not impossible. In problems where accurate (forward) models are lacking, Deep Reinforcement Learning (RL) has shown to be a viable solution to map observations (e.g. images) to good interactions in the form of close-loop visuomotor policies. However, Deep RL is sample inefficient and fails when applied directly to the problem of unoccluding objects based on images. In this work we present a novel Deep RL procedure that combines i) teacher-aided exploration, ii) a critic with privileged information, and iii) mid-level representations, resulting in sample efficient and effective learning for the problem of uncovering a target object occluded by a heap of unknown objects. Our experiments show that our approach trains faster and converges to more efficient uncovering solutions than baselines and ablations, and that our uncovering policies lead to an average improvement in the graspability of the target object, facilitating downstream retrieval applications. Andrey Kurenkov, Joseph Taglic, Rohun Kulkarni, Marcus Dominguez-Kuhne, Animesh Garg, Roberto Martin Martin, Silvio Savarese	IROS	5
2020	Causal Discovery in Physical Systems from Videos abstract Causal discovery is at the core of human cognition. It enables us to reason about the environment and make counterfactual predictions about unseen scenarios that can vastly differ from our previous experiences. We consider the task of causal discovery from videos in an end-to-end fashion without supervision on the ground-truth graph structure. In particular, our goal is to discover the structural dependencies among environmental and object variables: inferring the type and strength of interactions that have a causal effect on the behavior of the dynamical system. Our model consists of (a) a perception module that extracts a semantically meaningful and temporally consistent keypoint representation from images, (b) an inference module for determining the graph distribution induced by the detected keypoints, and (c) a dynamics module that can predict the future by conditioning on the inferred graph. We assume access to different configurations and environmental conditions, i.e., data from unknown interventions on the underlying system; thus, we can hope to discover the correct underlying causal graph without explicit interventions. We evaluate our method in a planar multi-body interaction environment and scenarios involving fabrics of different shapes like shirts and pants. Experiments demonstrate that our model can correctly identify the interactions from a short sequence of images and make long-term future predictions. The causal structure assumed by the model also allows it to make counterfactual predictions and extrapolate to systems of unseen interaction graphs or graphs of various sizes. Yunzhu Li, Antonio Torralba 0001, Anima Anandkumar, Dieter Fox, Animesh Garg	NeurIPS	5
2020	Counterfactual Data Augmentation using Locally Factored Dynamics abstract Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses. Though the subprocesses are not independent, their interactions are often sparse, and the dynamics at any given time step can often be decomposed into locally independent} causal mechanisms. Such local causal structures can be leveraged to improve the sample efficiency of sequence prediction and off-policy reinforcement learning. We formalize this by introducing local causal models (LCMs), which are induced from a global causal model by conditioning on a subset of the state space. We propose an approach to inferring these structures given an object-oriented state representation, as well as a novel algorithm for Counterfactual Data Augmentation (CoDA). CoDA uses local structures and an experience replay to generate counterfactual experiences that are causally valid in the global model. We find that CoDA significantly improves the performance of RL agents in locally factored tasks, including the batch-constrained and goal-conditioned settings. Code available at https://github.com/spitis/mrl. Silviu Pitis, Elliot Creager, Animesh Garg	NeurIPS	3
2020	Curriculum By Smoothing abstract Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in Generative Adversarial Networks (GANs) has highlighted the importance of learning by progressively increasing the difficulty of a learning task Kerras et al. When learning a network from scratch, the information propagated within the network during the earlier stages of training can contain distortion artifacts due to noise which can be detrimental to training. In this paper, we propose an elegant curriculum-based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. We propose to augment the training of CNNs by controlling the amount of high frequency information propagated within the CNNs as training progresses, by convolving the output of a CNN feature map of each layer with a Gaussian kernel. By decreasing the variance of the Gaussian kernel, we gradually increase the amount of high-frequency information available within the network for inference. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data. Our proposed augmented training scheme significantly improves the performance of CNNs on various vision tasks without either adding additional trainable parameters or an auxiliary regularization objective. The generality of our method is demonstrated through empirical performance gains in CNN architectures across four different tasks: transfer learning, cross-task transfer learning, and generative models. Samarth Sinha, Animesh Garg, Hugo Larochelle	NeurIPS	2
2020	OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation abstract Real-world tasks often exhibit a compositional structure that contains a sequence of simpler sub-tasks. For instance, opening a door requires reaching, grasping, rotating, and pulling the door knob. Such compositional tasks require an agent to reason about the sub-task at hand while orchestrating global behavior accordingly. This can be cast as an online task inference problem, where the current task identity, represented by a context variable, is estimated from the agent’s past experiences with probabilistic inference. Previous approaches have employed simple latent distributions, e.g., Gaussian, to model a single context for the entire task. However, this formulation lacks the expressiveness to capture the composition and transition of the sub-tasks. We propose a variational inference framework OCEAN to perform online task inference for compositional tasks. OCEAN models global and local context variables in a joint latent space, where the global variables represent a mixture of sub-tasks required for the task, while the local variables capture the transitions between the sub-tasks. Our framework supports flexible latent distributions based on prior knowledge of the task structure and can be trained in an unsupervised manner. Experimental results show that OCEAN provides more effective task inference with sequential context adaptation and thus leads to a performance boost on complex, multi-stage tasks. Hongyu Ren, Yuke Zhu, Jure Leskovec, Anima Anandkumar, Animesh Garg	UAI	5
2020	Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks abstract Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. It is nontrivial to manually design a robot controller that combines these modalities, which have very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to train directly on real robots due to sample complexity. In this article, we use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample efficiency of our policy learning. Evaluating our method on a peg insertion task, we show that it generalizes over varying geometries, configurations, and clearances, while being robust to external perturbations. We also systematically study different self-supervised learning objectives and representation learning architectures. Results are presented in simulation and on a physical robot. Michelle A. Lee, Yuke Zhu, Peter Zachares, Matthew Tan, Krishnan Srinivasan, Silvio Savarese, Li Fei-Fei 0001, Animesh Garg, Jeannette Bohg	IEEE Trans. Robotics	8
2019	Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration abstract Our goal is to generate a policy to complete an unseen task given just a single video demonstration of the task in a given domain. We hypothesize that to successfully generalize to unseen complex tasks from a single video demonstration, it is necessary to explicitly incorporate the compositional structure of the tasks into the model. To this end, we propose Neural Task Graph (NTG) Networks, which use conjugate task graph as the intermediate representation to modularize both the video demonstration and the derived policy. We empirically show NTG achieves inter-task generalization on two complex tasks: Block Stacking in BulletPhysics and Object Collection in AI2-THOR. NTG improves data efficiency with visual input as well as achieve strong generalization without the need for dense hierarchical supervision. We further show that similar performance trends hold when applied to real-world data. We show that NTG can effectively predict task structure on the JIGSAWS surgical dataset and generalize to unseen tasks. De-An Huang, Suraj Nair 0003, Danfei Xu, Yuke Zhu, Animesh Garg, Li Fei-Fei 0001, Silvio Savarese, Juan Carlos Niebles	CVPR	5
2019	Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter abstract When operating in unstructured environments such as warehouses, homes, and retail centers, robots are frequently required to interactively search for and retrieve specific objects from cluttered bins, shelves, or tables. Mechanical Search describes the class of tasks where the goal is to locate and extract a known target object. In this paper, we formalize Mechanical Search and study a version where distractor objects are heaped over the target object in a bin. The robot uses an RGBD perception system and control policies to iteratively select, parameterize, and perform one of 3 actions - push, suction, grasp - until the target object is extracted, or either a time limit is exceeded, or no high confidence push or grasp is available. We present a study of 5 algorithmic policies for mechanical search, with 15,000 simulated trials and 300 physical trials for heaps ranging from 10 to 20 objects. Results suggest that success can be achieved in this long-horizon task with algorithmic policies in over 95% of instances and that the number of actions required scales approximately linearly with the size of the heap. Code and supplementary material can be found at http://ai.stanford.edu/mech-search. Michael Danielczuk, Andrey Kurenkov, Ashwin Balakrishna, Matthew Matl, Roberto Martin Martin, Animesh Garg, Silvio Savarese, Kenneth Y. Goldberg	ICRA	7
2019	Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks abstract Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. However, it is non-trivial to manually design a robot controller that combines modalities with very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to deploy on real robots due to sample complexity. We use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample efficiency of our policy learning. We evaluate our method on a peg insertion task, generalizing over different geometry, configurations, and clearances, while being robust to external perturbations. We present results in simulation and on a real robot. Michelle A. Lee, Yuke Zhu, Krishnan Srinivasan, Parth Shah 0003, Silvio Savarese, Li Fei-Fei 0001, Animesh Garg, Jeannette Bohg	ICRA	7
2019	Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning abstract We address one-shot imitation learning, where the goal is to execute a previously unseen task based on a single demonstration. While there has been exciting progress in this direction, most of the approaches still require a few hundred tasks for meta-training, which limits the scalability of the approaches. Our main contribution is to formulate one-shot imitation learning as a symbolic planning problem along with the symbol grounding problem. This formulation disentangles the policy execution from the inter-task generalization and leads to better data efficiency. The key technical challenge is that the symbol grounding is prone to error with limited training data and leads to subsequent symbolic planning failures. We address this challenge by proposing a continuous relaxation of the discrete symbolic planner that directly plans on the probabilistic outputs of the symbol grounding model. Our continuous relaxation of the planner can still leverage the information contained in the probabilistic symbol grounding and significantly improve over the baseline planner for the one-shot imitation learning tasks without using large training data. De-An Huang, Danfei Xu, Yuke Zhu, Animesh Garg, Silvio Savarese, Li Fei-Fei 0001, Juan Carlos Niebles	IROS	4
2019	Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity abstract Large, richly annotated datasets have accelerated progress in fields such as computer vision and natural language processing, but replicating these successes in robotics has been challenging. While prior data collection methodologies such as self-supervision have resulted in large datasets, the data can have poor signal-to-noise ratio. By contrast, previous efforts to collect task demonstrations with humans provide better quality data, but they cannot reach the same data magnitude. Furthermore, neither approach places guarantees on the diversity of the data collected, in terms of solution strategies. In this work, we leverage and extend the RoboTurk platform to scale up data collection for robotic manipulation using remote teleoperation. The primary motivation for our platform is two-fold: (1) to address the shortcomings of prior work and increase the total quantity of manipulation data collected through human supervision by an order of magnitude without sacrificing the quality of the data and (2) to collect data on challenging manipulation tasks across several operators and observe a diverse set of emergent behaviors and solutions. We collected over 111 hours of robot manipulation data across 54 users and 3 challenging manipulation tasks in 1 week, resulting in the largest robot dataset collected via remote teleoperation. We evaluate the quality of our platform, the diversity of demonstrations in our dataset, and the utility of our dataset via quantitative and qualitative analysis. For additional results, supplementary videos, and to download our dataset, visit http;//roboturk.stanford.edu/realrobotdataset. Ajay Mandlekar, Jonathan Booher, Max Spero, Albert Tung, Anchit Gupta, Yuke Zhu, Animesh Garg, Silvio Savarese, Li Fei-Fei 0001	IROS	7
2019	Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks abstract Reinforcement Learning (RL) of contact-rich manipulation tasks has yielded impressive results in recent years. While many studies in RL focus on varying the observation space or reward model, few efforts focused on the choice of action space (e.g. joint or end-effector space, position, velocity, etc.). However, studies in robot motion control indicate that choosing an action space that conforms to the characteristics of the task can simplify exploration and improve robustness to disturbances. This paper studies the effect of different action spaces in deep RL and advocates for variable impedance control in end-effector space (VICES) as an advantageous action space for constrained and contact-rich tasks. We evaluate multiple action spaces on three prototypical manipulation tasks: Path Following (task with no contact), Door Opening (task with kinematic constraints), and Surface Wiping (task with continuous contact). We show that VICES improves sample efficiency, maintains low energy consumption, and ensures safety across all three experimental setups. Further, RL policies learned with VICES can transfer across different robot models in simulation, and from simulation to real for the same robot. Further information is available at https://stanfordvl.github.io/vices. Roberto Martin Martin, Michelle A. Lee, Rachel Gardner, Silvio Savarese, Jeannette Bohg, Animesh Garg	IROS	6
2018	Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos abstract Grounding textual phrases in visual content with standalone image-sentence pairs is a challenging task. When we consider grounding in instructional videos, this problem becomes profoundly more complex: the latent temporal structure of instructional videos breaks independence assumptions and necessitates contextual understanding for resolving ambiguous visual-linguistic cues. Furthermore, dense annotations and video data scale mean supervised approaches are prohibitively costly. In this work, we propose to tackle this new task with a weakly-supervised framework for reference-aware visual grounding in instructional videos, where only the temporal alignment between the transcription and the video segment are available for supervision. We introduce the visually grounded action graph, a structured representation capturing the latent dependency between grounding and references in video. For optimization, we propose a new reference-aware multiple instance learning (RA-MIL) objective for weak supervision of grounding in videos. We evaluate our approach over unconstrained videos from YouCookII and RoboWatch, augmented with new reference-grounding test set annotations. We demonstrate that our jointly optimized, reference-aware approach simultaneously improves visual grounding, reference-resolution, and generalization to unseen instructional video categories. De-An Huang, Shyamal Buch, Lucio M. Dery, Animesh Garg, Li Fei-Fei 0001, Juan Carlos Niebles	CVPR	4
2018	Neural Task Programming: Learning to Generalize Across Hierarchical Tasks abstract In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes as input a task specification (e.g., video demonstration of a task) and recursively decomposes it into finer sub-task specifications. These specifications are fed to a hierarchical neural program, where bottom-level programs are callable subroutines that interact with the environment. We validate our method in three robot manipulation tasks. NTP achieves strong generalization across sequential tasks that exhibit hierarchal and compositional structures. The experimental results show that NTP learns to generalize well towards unseen tasks with increasing lengths, variable topologies, and changing objectives.stanfordvl.github.io/ntp/. Danfei Xu, Suraj Nair 0003, Yuke Zhu, Julian Gao, Animesh Garg, Li Fei-Fei 0001, Silvio Savarese	ICRA	5
2018	DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image abstract 3D reconstruction from a single image is a key problem in multiple applications ranging from robotic manipulation to augmented reality. Prior methods have tackled this problem through generative models which predict 3D reconstructions as voxels or point clouds. However, these methods can be computationally expensive and miss fine details. We introduce a new differentiable layer for 3D data deformation and use it in DEFORMNET to learn a model for 3D reconstruction-through-deformation. DEFORMNET takes an image input, finds a nearest shape template from a database, and deforms the template to match the query image. We evaluate our approach on the ShapeNet dataset and show that - (a) the Free-Form Deformation layer is a powerful new building block for Deep Learning models that manipulate 3D data (b) DEFORMNET uses this FFD layer combined with shape retrieval for smooth and detail-preserving 3D reconstruction of qualitatively plausible point clouds with respect to a single query image (c) compared to other state-of-the-art 3D reconstruction methods, DEFORMNET quantitatively matches or outperforms their benchmarks by significant margins. Andrey Kurenkov, Jingwei Ji, Animesh Garg, Viraj Mehta, JunYoung Gwak, Christopher B. Choy, Silvio Savarese	WACV	3
2017	Weakly Supervised 3D Reconstruction with Adversarial Constraint abstract Supervised 3D reconstruction has witnessed a significant progress through the use of deep neural networks. However, this increase in performance requires large scale annotations of 2D/3D data. In this paper, we explore inexpensive 2D supervision as an alternative for expensive 3D CAD annotation. Specifically, we use foreground masks as weak supervision through a raytrace pooling layer that enables perspective projection and backpropagation. Additionally, since the 3D reconstruction from masks is an ill posed problem, we propose to constrain the 3D reconstruction to the manifold of unlabeled realistic 3D shapes that match mask observations. We demonstrate that learning a log-barrier solution to this constrained optimization problem resembles the GAN objective, enabling the use of existing tools for training GANs. We evaluate and analyze the manifold constrained reconstruction on various datasets for single and multi-view reconstruction of both synthetic and real images. JunYoung Gwak, Christopher B. Choy, Manmohan Krishna Chandraker, Animesh Garg, Silvio Savarese	3DV	4
2017	Multilateral surgical pattern cutting in 2D orthotropic gauze with deep reinforcement learning policies for tensioning abstract In the Fundamentals of Laparoscopic Surgery (FLS) standard medical training regimen, the Pattern Cutting task requires residents to demonstrate proficiency by maneuvering two tools, surgical scissors and tissue gripper, to accurately cut a circular pattern on surgical gauze suspended at the corners. Accuracy of cutting depends on tensioning, wherein the gripper pinches a point on the gauze in R3and pulls to induce and maintain tension in the material as cutting proceeds. An automated tensioning policy maps the current state of the gauze to output a direction of pulling as an action. The optimal tensioning policy depends on both the choice of pinch point and cutting trajectory. We explore the problem of learning a tensioning policy conditioned on specific cutting trajectories. Every timestep, we allow the gripper to react to the deformation of the gauze and progress of the cutting trajectory with a translation unit vector along an allowable set of directions. As deformation is difficult to analytically model and explicitly observe, we leverage deep reinforcement learning with direct policy search methods to learn tensioning policies using a finite-element simulator and then transfer them to a physical system. We compare the Deep RL tensioning policies with fixed and analytic (opposing the error vector with a fixed pinch point) policies on a set of 17 open and closed curved contours in simulation and 4 patterns in physical experiments with the da Vinci Research Kit (dVRK). Our simulation results suggest that learning to tension with Deep RL can significantly improve performance and robustness to noise and external forces. Brijen Thananjeyan, Animesh Garg, Sanjay Krishnan, Carolyn Chen, Lauren Miller, Kenneth Y. Goldberg	ICRA	2
2017	Adversarially Robust Policy Learning: Active construction of physically-plausible perturbations abstract Policy search methods in reinforcement learning have demonstrated success in scaling up to larger problems beyond toy examples. However, deploying these methods on real robots remains challenging due to the large sample complexity required during learning and their vulnerability to malicious intervention. We introduce Adversarially Robust Policy Learning (ARPL), an algorithm that leverages active computation of physically-plausible adversarial examples during training to enable robust policy learning in the source domain and robust performance under both random and adversarial input perturbations. We evaluate ARPL on four continuous control tasks and show superior resilience to changes in physical environment dynamics parameters and environment state as compared to state-of-the-art robust policy learning methods. Code, data, and additional experimental results are available at: stanfordvl.github.io/ARPL. Ajay Mandlekar, Yuke Zhu, Animesh Garg, Li Fei-Fei 0001, Silvio Savarese	IROS	3
2017	AdaPT: Zero-Shot Adaptive Policy Transfer for Stochastic Dynamical Systems James Harrison, Animesh Garg, Boris Ivanovic, Yuke Zhu, Silvio Savarese, Li Fei-Fei 0001, Marco Pavone 0001	ISRR	2
2016	TSC-DL: Unsupervised trajectory segmentation of multi-modal surgical demonstrations with Deep Learning abstract The growth of robot-assisted minimally invasive surgery has led to sizable datasets of fixed-camera video and kinematic recordings of surgical subtasks. Segmentation of these trajectories into locally-similar contiguous sections can facilitate learning from demonstrations, skill assessment, and salvaging good segments from otherwise inconsistent demonstrations. Manual, or supervised, segmentation can be prone to error and impractical for large datasets. We present Transition State Clustering with Deep Learning (TSC-DL), a new unsupervised algorithm that leverages video and kinematic data for task-level segmentation, and finds regions of the visual feature space that correlate with transition events using features constructed from layers of pre-trained image classification Deep Convolutional Neural Networks (CNNs). We report results on three datasets comparing Deep Learning architectures (AlexNet and VGG), choice of convolutional layer, dimensionality reduction techniques, visual encoding, and the use of Scale Invariant Feature Transforms (SIFT). We find that the deep architectures extract features that result in up-to a 30.4% improvement in Silhouette Score (a measure of cluster tightness) over the traditional “shallow” features from SIFT. We also present cases where TSC-DL discovers human annotator omissions. Supplementary material, data and code is available at: http://berkeleyautomation.github.io/tsc-dl/. Adithyavairavan Murali, Animesh Garg, Sanjay Krishnan, Florian T. Pokorny, Pieter Abbeel, Trevor Darrell, Kenneth Y. Goldberg	ICRA	2
2016	Automating multi-throw multilateral surgical suturing with a mechanical needle guide and sequential convex optimization abstract For supervised automation of multi-throw suturing in Robot-Assisted Minimally Invasive Surgery, we present a novel mechanical needle guide and a framework for optimizing needle size, trajectory, and control parameters using sequential convex programming. The Suture Needle Angular Positioner (SNAP) results in a 3x error reduction in the needle pose estimate in comparison with the standard actuator. We evaluate the algorithm and SNAP on a da Vinci Research Kit using tissue phantoms and compare completion time with that of humans from the JIGSAWS dataset [5]. Initial results suggest that the dVRK can perform suturing at 30% of human speed while completing 86% suture throws attempted. Videos and data are available at: berkeleyautomation.github.io/amts. Siddarth Sen, Animesh Garg, David V. Gealy, Stephen McKinley, Yiming Jen, Kenneth Y. Goldberg	ICRA	2
2016	SWIRL: A SequentialWindowed Inverse Reinforcement Learning Algorithm for Robot Tasks With Delayed Rewards Sanjay Krishnan, Animesh Garg, Richard Liaw, Brijen Thananjeyan, Lauren Miller, Florian T. Pokorny, Kenneth Y. Goldberg	WAFR	2
2015	Learning by observation for surgical subtasks: Multilateral cutting of 3D viscoelastic and 2D Orthotropic Tissue Phantoms abstract Automating repetitive surgical subtasks such as suturing, cutting and debridement can reduce surgeon fatigue and procedure times and facilitate supervised tele-surgery. Programming is difficult because human tissue is deformable and highly specular. Using the da Vinci Research Kit (DVRK) robotic surgical assistant, we explore a “Learning By Observation” (LBO) approach where we identify, segment, and parameterize motion sequences and sensor conditions to build a finite state machine (FSM) for each subtask. The robot then executes the FSM repeatedly to tune parameters and if necessary update the FSM structure. We evaluate the approach on two surgical subtasks: debridement of 3D Viscoelastic Tissue Phantoms (3d-DVTP), in which small target fragments are removed from a 3D viscoelastic tissue phantom; and Pattern Cutting of 2D Orthotropic Tissue Phantoms (2d-PCOTP), a step in the standard Fundamentals of Laparoscopic Surgery training suite, in which a specified circular area must be cut from a sheet of orthotropic tissue phantom. We describe the approach and physical experiments with repeatability of 96% for 50 trials of the 3d-DVTP subtask and 70% for 20 trials of the 2d-PCOTP subtask. A video is available at: http://j.mp/Robot-Surgery-Video-Oct-2014. Adithyavairavan Murali, Siddarth Sen, Ben Kehoe, Animesh Garg, Seth McFarland, Sachin Patil, W. Douglas Boyd, Susan Lim, Pieter Abbeel, Kenneth Y. Goldberg	ICRA	4
2015	Transition State Clustering: Unsupervised Surgical Trajectory Segmentation for Robot Learning Sanjay Krishnan, Animesh Garg, Sachin Patil, Colin Lea, Gregory D. Hager, Pieter Abbeel, Kenneth Y. Goldberg	ISRR (2)	2
2013	Robot-Guided Open-Loop Insertion of Skew-Line Needle Arrangements for High Dose Rate Brachytherapy abstract We present a study in human-centered automation that has potential to reduce patient side effects from high dose rate brachytherapy (HDR-BT). To efficiently deliver radiation to the prostate while minimizing trauma to sensitive structures such as the penile bulb, we modified the Acubot-RND 7-axis robot to guide insertion of diamond-tip needles into desired skew-line geometric arrangements. We extend and integrate two algorithms: Needle Planning with Integer Programming (NPIP) and Inverse Planning with Integer Programming (IPIP) to compute skew-line needle and dose plans. We performed three physical experiments with anatomically correct phantom models to study performance: two with the robot and one control experiment with an expert human physician (coauthor Hsu) without the robot. All were able to achieve needle arrangements that meet the RTOG-0321 clinical dose objectives with zero trauma to the penile bulb. We analyze systematic and random errors in needle placement; total RMS error for the robot system operating without feedback ranged from 2.6 to 4.3 mm, which is comparable to the RMS error of 2.7 mm obtained in an earlier study for PPI-BT treatment using a robot with 3D ultrasound feedback. Animesh Garg, Timmy Siauw, Dmitry Berenson, J. Adam M. Cunha, I-Chow Hsu, Jean Pouliot, Dan Stoianovici, Kenneth Y. Goldberg	IEEE Trans Autom. Sci. Eng.	1