Dorsa Sadigh

EDBT 2026 Demo / reviewers in the wild / expert

dblp:117/3174 · DBLP profile ↗

← Back

82ranked-venue papers

2as first author

62since 2021 · last 2025

0000-0002-7802-9183ORCID · verified

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

Artificial intelligence and machine learning · 73 · 1 first-author · 60 since 2021Systems, architecture and hardware · 31 · 1 first-author · 22 since 2021Human-computer interaction and ubiquitous computing · 7 · 6 since 2021Graphics, computer vision, multimedia, augmented reality and games · 4 · 4 since 2021Theory of computation · 4 · 1 first-authorSoftware engineering, systems software and programming languages · 3 · 1 first-authorApplied, interdisciplinary, general and emerging computing · 3 · 2 since 2021

Year	Publication	Venue	Position
2025	Shared Autonomy for Proximal Teaching abstract Motor skills education often requires experienced professionals who can provide personalized instruction. Unfortu-nately, the availability of high-quality training can be limited for specialized tasks, such as high performance racing. Several recent works have proposed AI -assistance for motor skills instruction, ranging from rehabilitation to surgical robot tele-operation. However, these works often make simplifying assumptions on the student learning process, and fail to model how a teacher's assistance interacts with different individuals' abilities when determining optimal teaching strategies. Inspired by the idea of scaffolding from educational psychology, we leverage shared autonomy, a framework for combining user inputs with robot autonomy, to aid with curriculum design. Our key insight is that the way a student's behavior improves in the presence of assistance from an autonomous agent can highlight which sub-skills might be most “learnable” for the student, or within their Zone of Proximal Development. We use this to design Z-COACH, a method for using shared autonomy to provide personalized instruction targeting interpretable task sub-skills. In a user study$(\mathrm{n}=50)$, where we teach high performance racing in a simulated environment of the Thunderhill Raceway Park with the CARLA Autonomous Driving simulator, we show that Z-COACH helps identify which skills each student should first practice, leading to an overall improvement in driving time, behavior, and smoothness. Our work shows that increasingly available semi-autonomous capabilities (e.g. in vehicles, robots) can not only assist human users, but also help teach them. Megha Srivastava, Reihaneh Iranmanesh, Yuchen Cui, Deepak Edakkattil Gopinath, Emily S. Sumner, Andrew Silva, Laporsha Dees, Guy Rosman, Dorsa Sadigh	HRI	9
2025	Vision Language Models are In-Context Value Learners abstract Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and domains requires both a large amount of diverse data and methods which can scale and generalize. To address these challenges, we present Generative Value Learning (GVL), a universal value function estimator that leverages the world knowledge embedded in vision-language models (VLMs) to predict task progress. Naively asking a VLM to predict values for a video sequence performs poorly due to the strong temporal correlation between successive frames. Instead, GVL poses value estimation as a temporal ordering problem over shuffled video frames; this seemingly more challenging task encourages VLMs to more fully exploit their underlying semantic and temporal grounding capabilities to differentiate frames based on their perceived task progress, consequently producing significantly better value predictions. Without any robot or task specific training, GVL can in-context zero-shot and few-shot predict effective values for more than 300 distinct real-world tasks across diverse robot platforms, including challenging bimanual manipulation tasks. Furthermore, we demonstrate that GVL permits flexible multi-modal in-context learning via examples from heterogeneous tasks and embodiments, such as human videos. The generality of GVL enables various downstream applications pertinent to visuomotor policy learning, including dataset filtering, success detection, and value-weighted regression -- all without any model training or finetuning. Yecheng Jason Ma 0001, Joey Hejna, Chuyuan Fu, Dhruv Shah, Jacky Liang, Sean Kirmani, Peng Xu 0010, Danny Drieß, Ted Xiao, Osbert Bastani, Dinesh Jayaraman, Wenhao Yu 0003, Tingnan Zhang, Dorsa Sadigh, Fei Xia 0002	ICLR	15
2025	What's the Move? Hybrid Imitation Learning via Salient Points abstract While imitation learning (IL) offers a promising framework for teaching robots various behaviors, learning complex tasks remains challenging. Existing IL policies struggle to generalize effectively across visual and spatial variations even for simple tasks. In this work, we introduce SPHINX: Salient Point-based Hybrid ImitatioN and eXecution, a flexible IL policy that leverages multimodal observations (point clouds and wrist images), along with a hybrid action space of low-frequency, sparse waypoints and high-frequency, dense end effector movements. Given 3D point cloud observations, SPHINX learns to infer task-relevant points within a point cloud, or salient points, which support spatial generalization by focusing on semantically meaningful features. These salient points serve as anchor points to predict waypoints for long-range movement, such as reaching target poses in free-space. Once near a salient point, SPHINX learns to switch to predicting dense end-effector movements given close-up wrist images for precise phases of a task. By exploiting the strengths of different input modalities and action representations for different manipulation phases, SPHINX tackles complex tasks in a sample-efficient, generalizable manner. Our method achieves 86.7% success across 4 real-world and 2 simulated tasks, outperforming the next best state-of-the-art IL baseline by 41.1% on average across 440 real world trials. SPHINX additionally generalizes to novel viewpoints, visual distractors, spatial arrangements, and execution speeds with a 1.7x speedup over the most competitive baseline. Our website (http://sphinx-manip.github.io) provides open-sourced code for data collection, training, and evaluation, along with supplementary videos. Priya Sundaresan, Hengyuan Hu, Jeannette Bohg, Dorsa Sadigh	ICLR	5
2025	Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation abstract Denoising Diffusion Probabilistic Models (DDPMs) have emerged as powerful tools for generative modeling. However, their sequential computation requirements lead to significant inference-time bottlenecks. In this work, we utilize the connection between DDPMs and Stochastic Localization to prove that, under an appropriate reparametrization, the increments of DDPM satisfy an exchangeability property. This general insight enables near-black-box adaptation of various performance optimization techniques from autoregressive models to the diffusion setting. To demonstrate this, we introduce Autospeculative Decoding (ASD), an extension of the widely used speculative decoding algorithm to DDPMs that does not require any auxiliary draft models. Our theoretical analysis shows that ASD achieves a $\tilde{O}(K^{\frac{1}{3}})$ parallel runtime speedup over the $K$ step sequential DDPM. We also demonstrate that a practical implementation of autospeculative decoding accelerates DDPM inference significantly in various domains. Hengyuan Hu, Aniket Das, Dorsa Sadigh, Nima Anari	ICML	3
2025	Latent Diffusion Planning for Imitation Learning abstract Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert demonstrations. To address these shortcomings, we propose Latent Diffusion Planning (LDP), a modular approach consisting of a planner which can leverage action-free demonstrations, and an inverse dynamics model which can leverage suboptimal data, that both operate over a learned latent space. First, we learn a compact latent space through a variational autoencoder, enabling effective forecasting of future states in image-based domains. Then, we train a planner and an inverse dynamics model with diffusion objectives. By separating planning from action prediction, LDP can benefit from the denser supervision signals of suboptimal and action-free data. On simulated visual robotic manipulation tasks, LDP outperforms state-of-the-art imitation learning approaches, as they cannot leverage such additional data. Amber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn	ICML	3
2025	Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning abstract Expressive robotic behavior is essential for the widespread acceptance of robots in social environments. Recent advancements in learned legged locomotion controllers have enabled more dynamic and versatile robot behaviors. However, determining the optimal behavior for interactions with different users across varied scenarios remains a challenge. Current methods either rely on natural language input, which is efficient but low-resolution, or learn from human preferences, which, although high-resolution, is sample inefficient. This paper introduces a novel approach that leverages priors generated by pre- trained LLMs alongside the precision of preference learning. Our method, termed Language-Guided Preference Learning (LGPL), uses LLMs to generate initial behavior samples, which are then refined through preference-based feedback to learn behaviors that closely align with human expectations. Our core insight is that LLMs can guide the sampling process for preference learning, leading to a substantial improvement in sample efficiency. We demonstrate that LGPL can quickly learn accurate and expressive behaviors with as few as four queries, outperforming both purely language-parameterized models and traditional preference learning approaches. Website with videos: this http url. Jaden Clark, Joey Hejna, Dorsa Sadigh	ICRA	3
2025	How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learning abstract Imitation learning is a promising approach for learning robot policies with user-provided data. The way demonstrations are provided, i.e., demonstration modality, influences the quality of the data. While existing research shows that kinesthetic teaching (physically guiding the robot) is preferred by users for the intuitiveness and ease of use, the majority of existing manipulation datasets were collected through teleoperation via a VR controller or spacemouse. In this work, we investigate how different demonstration modalities impact downstream learning performance as well as user experience. Specifically, we compare low-cost demonstration modalities including kinesthetic teaching, teleoperation with a VR controller, and teleoperation with a spacemouse controller. We experiment with three table-top manipulation tasks with different motion constraints. We evaluate and compare imitation learning performance using data from different demonstration modalities, and collected subjective feedback on user experience. Our results show that kinesthetic teaching is rated the most intuitive for controlling the robot and provides cleanest data for best downstream learning performance. However, it is not preferred as the way for large-scale data collection due to the physical load. Based on such insight, we propose a simple data collection scheme that relies on a small number of kinesthetic demonstrations mixed with data collected through teleoperation to achieve the best overall learning performance while maintaining low data-collection effort. Haozhuo Li, Yuchen Cui, Dorsa Sadigh	ICRA	3
2025	RoboCrowd: Scaling Robot Data Collection Through Crowdsourcing abstract In recent years, imitation learning from large-scale human demonstrations has emerged as a promising paradigm for training robot policies. However, the burden of collecting large quantities of human demonstrations is significant in terms of collection time and the need for access to expert operators. We introduce a new data collection paradigm, RoboCrowd, which distributes the workload by utilizing crowdsourcing principles and incentive design. RoboCrowd helps enable scalable data collection and facilitates more efficient learning of robot policies. We build RoboCrowd on top of ALOHA [1]—a bimanual platform that supports data collection via puppeteering—to explore the design space for crowdsourcing in-person demonstrations in a public environment. We propose three classes of incentive mechanisms to appeal to users' varying sources of motivation for interacting with the system: material rewards, intrinsic interest, and social comparison. We instantiate these incentives through tasks that include physical rewards, engaging or challenging manipulations, as well as gamification elements such as a leaderboard. We conduct a large-scale, two-week field experiment in which the platform is situated in a university café. We observe significant engagement with the system—over 200 individuals independently volunteered to provide a total of over 800 interaction episodes. Our findings validate the proposed incentives as mechanisms for shaping users' data quantity and quality. Further, we demonstrate that the crowdsourced data can serve as useful pre-training data for policies fine-tuned on expert demonstrations—boosting performance up to 20 % compared to when this data is not available. These results suggest the potential for RoboCrowd to reduce the burden of robot data collection by carefully implementing crowdsourcing and incentive design principles. Videos are available at https://robocrowd.github.io. Suvir Mirchandani, David Yuan 0001, Kaylee Burns, Md Sazzad Islam, Tony Z. Zhao, Chelsea Finn, Dorsa Sadigh	ICRA	7
2025	RT-Affordance: Affordances are Versatile Intermediate Representations for Robot Manipulation abstract We explore how intermediate policy representations can facilitate generalization by providing guidance on how to perform manipulation tasks. Existing representations such as language, goal images, and trajectory sketches have been shown to be helpful, but these representations either do not provide enough context or provide over-specified context that yields less robust policies. We propose conditioning policies on affordances, which capture the pose of the robot at key stages of the task. Affordances offer expressive yet lightweight abstractions, are easy for users to specify, and facilitate efficient learning by transferring knowledge from large internet datasets. Our method, RT-Affordance, is a hierarchical model that first proposes an affordance plan given the task language, and then conditions the policy on this affordance plan to perform manipulation. Our model can flexibly bridge heterogeneous sources of supervision including large web datasets and robot trajectories. We additionally train our model on cheap-to-collect in-domain affordance images, allowing us to learn new tasks without collecting any additional costly robot trajectories. We show on a diverse set of novel tasks how RT-Affordance exceeds the performance of existing methods by over 50 %, and we empirically demonstrate that affordances are robust to novel settings. Videos available at https://snasiriany. me/rt-affordance Soroush Nasiriany, Sean Kirmani, Tianli Ding, Laura Smith 0001, Yuke Zhu, Danny Drieß, Dorsa Sadigh, Ted Xiao	ICRA	7
2025	Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning abstract Teaching robots to autonomously complete everyday tasks remains a challenge. Imitation Learning (IL) is a powerful approach that imbues robots with skills via demonstrations, but is limited by the labor-intensive process of collecting teleoperated robot data. Human videos offer a scalable alternative, but it remains difficult to directly train IL policies from them due to the lack of robot action labels. To address this, we propose to represent actions as short-horizon 2D trajectories on an image. These actions, or motion tracks, capture the predicted direction of motion for both human hands and robot end-effectors. We instantiate an IL policy called Motion Track Policy (MT-$\pi$) which receives image observations and outputs motion tracks as actions. By leveraging this unified, cross-embodiment action space, MT-$\pi$completes tasks with high success given just minutes of human video and limited additional robot demonstrations. At test time, we predict motion tracks from two camera views, recovering 6DoF trajectories via multi-view synthesis. MT-$\pi$achieves an average success rate of 86.5% across 4 real-world tasks, outperforming state-of-the-art IL baselines which do not leverage human data or our action space by 40%, and generalizes to scenarios seen only in human videos. Code and videos are available on our website (https://portal-cornell.github.io/motion_track_policy/). Juntao Ren, Priya Sundaresan, Dorsa Sadigh, Sanjiban Choudhury, Jeannette Bohg	ICRA	3
2025	Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning Bidipta Sarkar, Warren Xia, C. Karen Liu, Dorsa Sadigh	AAMAS	4
2025	Scaffolding Dexterous Manipulation with Vision-Language Models abstract Dexterous robotic hands are essential for performing complex manipulation tasks, yet remain difficult to train due to the challenges of demonstration collection and high-dimensional control. While reinforcement learning (RL) can alleviate the data bottleneck by generating experience in simulation, it typically relies on carefully designed, task-specific reward functions, which hinder scalability and generalization. Thus, contemporary works in dexterous manipulation have often bootstrapped from reference trajectories. These trajectories specify target hand poses that guide the exploration of RL policies and object poses that enable dense, task-agnostic rewards. However, sourcing suitable trajectories---particularly for dexterous hands---remains a significant challenge. Yet, the precise details in explicit reference trajectories are often unnecessary, as RL ultimately refines the motion. Our key insight is that modern vision-language models (VLMs) already encode the commonsense spatial and semantic knowledge needed to specify tasks and guide exploration effectively. Given a task description (e.g., “open the cabinet”) and a visual scene, our method uses an off-the-shelf VLM to first identify task-relevant keypoints (e.g., handles, buttons) and then synthesize 3D trajectories for hand motion and object motion. Subsequently, we train a low-level residual RL policy in simulation to track these coarse trajectories or ``scaffolds'' with high fidelity. Across a number of simulated tasks involving articulated objects and semantic understanding, we demonstrate that our method is able to learn robust dexterous manipulation policies. Moreover, we showcase that our method transfers to real-world robotic hands without any human demonstrations or handcrafted rewards. Vincent de Bakker, Joey Hejna, Tyler Ga Wei Lum, Onur Celik, Aleksandar Taranovic, Denis Blessing, Gerhard Neumann, Jeannette Bohg, Dorsa Sadigh	NeurIPS	9
2024	SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities abstract Understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. While Vision Language Models (VLM) have demonstrated remarkable performance in certain VQA benchmarks, they still lack capabilities in 3D spatial reasoning, such as recognizing quantitative relationships of physical objects like distances or size difference. We hypothesize that VLMs' limited spatial reasoning capability is due to the lack of 3D spatial knowledge in training data and aim to solve this problem by training VLMs with Internet-scale spatial reasoning data. To this end, we present a system to facilitate this approach. We first develop an automatic 3D spatial VQA data generation framework that scales up to 2 billion VQA examples on 10 million real-world images. We then investigate various factors in training recipe including data quality, training pipeline and VLM architecture. Our workfeatures the first Internet-scale 3D spatial reasoning dataset in metric space. By training a VLM on such data, we significantly enhance its ability on both qual-itative and quantitative spatial VQA. Finally, we demonstrate that this VLM unlocks novel downstream applications in chain-of thought spatial reasoning and robotics due to its quantitative estimation capability. Website: https://spatial-vlm.github.iol Boyuan Chen 0003, Sean Kirmani, Brian Ichter, Dorsa Sadigh, Leonidas J. Guibas, Fei Xia 0002	CVPR	5
2024	Generative Expressive Robot Behaviors using Large Language Models abstract People employ expressive behaviors to effectively communicate and coordinate their actions with others, such as nodding to acknowledge a person glancing at them or saying "excuse me" to pass people in a busy corridor. We would like robots to also demonstrate expressive behaviors in human-robot interaction. Prior work proposes rule-based methods that struggle to scale to new communication modalities or social situations, while data-driven methods require specialized datasets for each social situation the robot is used in. We propose to leverage the rich social context available from large language models (LLMs) and their ability to generate motion based on instructions or user preferences, to generate expressive robot motion that is adaptable and composable, building upon each other. Our approach utilizes few-shot chain-of-thought prompting to translate human language instructions into parametrized control code using the robot's available and learned skills. Through user studies and simulation experiments, we demonstrate that our approach produces behaviors that users found to be competent and easy to understand. Supplementary material can be found at https://generative-expressive-motion.github.io/. Karthik Mahadevan, Jonathan Chien, Noah Brown, Carolina Parada, Fei Xia 0002, Andy Zeng 0001, Leila Takayama, Dorsa Sadigh	HRI	9
2024	Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning abstract Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second, align the model by optimizing the learned reward via reinforcement learning (RL). This paradigm assumes that human preferences are distributed according to reward, but recent work suggests that they instead follow the \emph{regret} under the user's optimal policy. Thus, learning a reward function from feedback is not only based on a flawed assumption of human preference, but also leads to unwieldy optimization challenges that stem from policy gradients or bootstrapping in the RL phase. Because of these optimization challenges, contemporary RLHF methods restrict themselves to contextual bandit settings (e.g., as in large language models) or limit observation dimensionality (e.g., state-based robotics). We overcome these limitations by introducing a new family of algorithms for optimizing behavior from human feedback using the \textit{regret}-based model of human preferences. Using the principle of maximum entropy, we derive \fullname (\abv), an algorithm for learning optimal policies from preferences without learning reward functions, circumventing the need for RL. \abv is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs. This enables \abv to elegantly scale to high-dimensional and sequential RLHF problems while being simpler than prior methods. Joey Hejna, Rafael Rafailov, Harshit Sikchi, Chelsea Finn, Scott Niekum, W. Bradley Knox, Dorsa Sadigh	ICLR	7
2024	Chain of Code: Reasoning with a Language Model-Augmented Code Emulator abstract Code provides a general syntactic structure to build complex programs and perform precise computations when paired with a code interpreter – we hypothesize that language models (LMs) can leverage code-writing to improve Chain of Thought reasoning not only for logic and arithmetic tasks, but also for semantic ones (and in particular, those that are a mix of both). For example, consider prompting an LM to write code that counts the number of times it detects sarcasm in an essay: the LM may struggle to write an implementation for "detect_sarcasm(string)" that can be executed by the interpreter (handling the edge cases would be insurmountable). However, LMs may still produce a valid solution if they not only write code, but also selectively "emulate" the interpreter by generating the expected output of "detect_sarcasm(string)". In this work, we propose Chain of Code (CoC), a simple yet surprisingly effective extension that improves LM code-driven reasoning. The key idea is to encourage LMs to format semantic sub-tasks in a program as flexible pseudocode that the interpreter can explicitly catch undefined behaviors and hand off to simulate with an LM (as an "LMulator"). Experiments demonstrate that Chain of Code outperforms Chain of Thought and other baselines across a variety of benchmarks; on BIG-Bench Hard, Chain of Code achieves 84%, a gain of 12% over Chain of Thought. In a nutshell, CoC broadens the scope of reasoning questions that LMs can answer by "thinking in code". Chengshu Li 0002, Jacky Liang, Andy Zeng 0001, Karol Hausman, Dorsa Sadigh, Sergey Levine, Li Fei-Fei 0001, Fei Xia 0002, Brian Ichter	ICML	6
2024	Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models abstract Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and PaLI-3. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored, making it challenging to understand what factors account for model performance – a challenge further complicated by the lack of objective, consistent evaluations. To address these gaps, we first compile a suite of standardized evaluations spanning visual question answering, object localization, and challenge sets that probe properties such as hallucination; evaluations that provide fine-grained insight VLM capabilities. Second, we rigorously investigate VLMs along key design axes, including pretrained visual representations and training from base vs. instruct-tuned language models, amongst others. We couple our analysis with three resource contributions: (1) a unified framework for evaluating VLMs, (2) optimized, flexible training code, and (3) checkpoints for all models, including a family of VLMs at the 7-13B scale that strictly outperform InstructBLIP and LLaVa v1.5, the state-of-the-art in open VLMs. Siddharth Karamcheti, Suraj Nair 0003, Ashwin Balakrishna, Percy Liang, Thomas Kollar, Dorsa Sadigh	ICML	6
2024	How to Prompt Your Robot: A PromptBook for Manipulation Skills with Code as Policies abstract Large Language Models (LLMs) have demonstrated the ability to perform semantic reasoning, planning and write code for robotics tasks. However, most methods rely on pre-existing primitives (i.e. pick, open drawer) or similar examples of robot code alone, which heavily limits their scalability to new scenarios. We present PromptBook, a collection of different prompting paradigms to generate code for successfully executing new manipulation skills. We demonstrate example-based, instruction-based and chain-of-thought to write robot code; as well as a method to build the prompt leveraging LLMs and human feedback. We show PromptBook enables LLMs to write code for new low-level manipulation skills in a zero-shot manner: from picking diverse objects, opening/closing drawers, to whisking, and waving hello. We evaluate the new skills on a mobile manipulator with 83% success rate at picking, 50-71% at opening drawers and 100% at closing them. Notably, the LLM is able to infer gripper orientation for grasping a drawer handle (z-axis aligned) vs. a top-down grasp (x-axis aligned). Montse Gonzalez Arenas, Ted Xiao, Sumeet Singh, Vidhi Jain, Allen Z. Ren, Jake Varley, Isabel Leal, Sean Kirmani, Mario Prats, Dorsa Sadigh, Vikas Sindhwani, Kanishka Rao, Jacky Liang, Andy Zeng 0001	ICRA	12
2024	Physically Grounded Vision-Language Models for Robotic Manipulation abstract Recent advances in vision-language models (VLMs) have led to improved performance on tasks such as visual question answering and image captioning. Consequently, these models are now well-positioned to reason about the physical world, particularly within domains such as robotic manipulation. However, current VLMs are limited in their understanding of the physical concepts (e.g., material, fragility) of common objects, which restricts their usefulness for robotic manipulation tasks that involve interaction and physical reasoning about such objects. To address this limitation, we propose PHYSOBJECTS, an object-centric dataset of 39.6K crowd-sourced and 417K automated physical concept annotations of common household objects. We demonstrate that fine-tuning a VLM on PhysObjects improves its understanding of physical object concepts, including generalization to held-out concepts, by capturing human priors of these concepts from visual appearance. We incorporate this physically grounded VLM in an interactive framework with a large language model-based robotic planner, and show improved planning performance on tasks that require reasoning about physical object concepts, compared to baselines that do not leverage physically grounded VLMs. We additionally illustrate the benefits of our physically grounded VLM on a real robot, where it improves task success rates. We release our dataset and provide further details and visualizations of our results at https://iliad.stanford.edu/pg-vlm/. Jensen Gao, Bidipta Sarkar, Fei Xia 0002, Ted Xiao, Jiajun Wu 0001, Brian Ichter, Anirudha Majumdar, Dorsa Sadigh	ICRA	8
2024	Toward Grounded Commonsense Reasoning abstract Consider a robot tasked with tidying a desk with a meticulously constructed Lego sports car. A human may recognize that it is not appropriate to disassemble the sports car and put it away as part of the "tidying." How can a robot reach that conclusion? Although large language models (LLMs) have recently been used to enable commonsense reasoning, grounding this reasoning in the real world has been challenging. To reason in the real world, robots must go beyond passively querying LLMs and actively gather information from the environment that is required to make the right decision. For instance, after detecting that there is an occluded car, the robot may need to actively perceive the car to know whether it is an advanced model car made out of Legos or a toy car built by a toddler. We propose an approach that leverages an LLM and vision language model (VLM) to help a robot actively perceive its environment to perform grounded commonsense reasoning. To evaluate our framework at scale, we release the MessySurfaces dataset which contains images of 70 real-world surfaces that need to be cleaned. We additionally illustrate our approach with a robot on 2 carefully designed surfaces. We find an average 12.9% improvement on the MessySurfaces benchmark and an average 15% improvement on the robot experiments over baselines that do not use active perception. The dataset, code, and videos of our approach can be found at https://minaek.github.io/grounded_commonsense_reasoning/. Minae Kwon, Hengyuan Hu, Vivek Myers, Siddharth Karamcheti, Anca D. Dragan, Dorsa Sadigh	ICRA	6
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	57
2024	Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections abstract Today’s robot policies exhibit subpar performance when faced with the challenge of generalizing to novel environments. Human corrective feedback is a crucial form of guidance to enable such generalization. However, adapting to and learning from online human corrections is a non-trivial endeavor: not only do robots need to remember human feedback over time to retrieve the right information in new settings and reduce the intervention rate, but also they would need to be able to respond to feedback that can be arbitrary corrections about high-level human preferences to low-level adjustments to skill parameters. In this work, we present Distillation and Retrieval of Online Corrections (DROC), a large language model (LLM)-based system that can respond to arbitrary forms of language feedback, distill generalizable knowledge from corrections, and retrieve relevant past experiences based on textual and visual similarity for improving performance in novel settings. DROC is able to respond to a sequence of online language corrections that address failures in both high-level task plans and low-level skill primitives. We demonstrate that DROC effectively distills the relevant information from the sequence of online corrections in a knowledge base and retrieves that knowledge in settings with new task or object instances. DROC outperforms other techniques that directly generate robot code via LLMs [1] by using only half of the total number of corrections needed in the first round and requires little to no corrections after two iterations. We show further results and videos on our project website: https://sites.google.com/stanford.edu/droc. Lihan Zha, Yuchen Cui, Li-Heng Lin, Minae Kwon, Montse Gonzalez Arenas, Andy Zeng 0001, Fei Xia 0002, Dorsa Sadigh	ICRA	8
2024	Batch Active Learning of Reward Functions from Human Preferences abstract Data generation and labeling are often expensive in robot learning. Preference-based learning is a concept that enables reliable labeling by querying users with preference questions. Active querying methods are commonly employed in preference-based learning to generate more informative data at the expense of parallelization and computation time. In this article, we develop a set of novel algorithms, batch active preference-based learning methods, that enable efficient learning of reward functions using as few data samples as possible while still having short query generation times and also retaining parallelizability. We introduce a method based on determinantal point processes for active batch generation and several heuristic-based alternatives. Finally, we present our experimental results for a variety of robotics tasks in simulation. Our results suggest that our batch active learning algorithm requires only a few queries that are computed in a short amount of time. We showcase one of our algorithms in a study to learn human users’ preferences. Erdem Biyik, Nima Anari, Dorsa Sadigh	ACM Trans. Hum. Robot Interact.	3
2023	No, to the Right: Online Language Corrections for Robotic Manipulation via Shared Autonomy abstract Systems for language-guided human-robot interaction must satisfy two key desiderata for broad adoption: adaptivity and learning efficiency. Unfortunately, existing instruction-following agents cannot adapt, lacking the ability to incorporate online natural language supervision, and even if they could, require hundreds of demonstrations to learn even simple policies. In this work, we address these problems by presenting Language-Informed Latent Actions with Corrections (LILAC), a framework for incorporating and adapting to natural language corrections "to the right", or "no, towards the book" - online, during execution. We explore rich manipulation domains within a shared autonomy paradigm. Instead of discrete turn-taking between a human and robot, LILAC splits agency between the human and robot: language is an input to a learned model that produces a meaningful, low-dimensional control space that the human can use to guide the robot. Each real-time correction refines the human's control space, enabling precise, extended behaviors - with the added benefit of requiring only a handful of demonstrations to learn. We evaluate our approach via a user study where users work with a Franka Emika Panda manipulator to complete complex manipulation tasks. Compared to existing learned baselines covering both open-loop instruction following and single-turn shared autonomy, we show that our corrections-aware approach obtains higher task completion rates, and is subjectively preferred by users because of its reliability, precision, and ease of use. Yuchen Cui, Siddharth Karamcheti, Raj Palleti, Nidhya Shivakumar, Percy Liang, Dorsa Sadigh	HRI	6
2023	Reward Design with Language Models Minae Kwon, Sang Michael Xie, Kalesha Bullard, Dorsa Sadigh	ICLR	4
2023	Distance Weighted Supervised Learning for Offline Interaction Data abstract Sequential decision making algorithms often struggle to leverage different sources of unstructured offline interaction data. Imitation learning (IL) methods based on supervised learning are robust, but require optimal demonstrations, which are hard to collect. Offline goal-conditioned reinforcement learning (RL) algorithms promise to learn from sub-optimal data, but face optimization challenges especially with high-dimensional data. To bridge the gap between IL and RL, we introduce Distance Weighted Supervised Learning or DWSL, a supervised method for learning goal-conditioned policies from offline data. DWSL models the entire distribution of time-steps between states in offline data with only supervised learning, and uses this distribution to approximate shortest path distances. To extract a policy, we weight actions by their reduction in distance estimates. Theoretically, DWSL converges to an optimal policy constrained to the data distribution, an attractive property for offline learning, without any bootstrapping. Across all datasets we test, DWSL empirically maintains behavior cloning as a lower bound while still exhibiting policy improvement. In high-dimensional image domains, DWSL surpasses the performance of both prior goal-conditioned IL and RL algorithms. Visualizations and code can be found at https://sites.google.com/view/dwsl/home. Joey Hejna, Jensen Gao, Dorsa Sadigh	ICML	3
2023	Language Instructed Reinforcement Learning for Human-AI Coordination abstract One of the fundamental quests of AI is to produce agents that coordinate well with humans. This problem is challenging, especially in domains that lack high quality human behavioral data, because multi-agent reinforcement learning (RL) often converges to different equilibria from the ones that humans prefer. We propose a novel framework, instructRL, that enables humans to specify what kind of strategies they expect from their AI partners through natural language instructions. We use pretrained large language models to generate a prior policy conditioned on the human instruction and use the prior to regularize the RL objective. This leads to the RL agent converging to equilibria that are aligned with human preferences. We show that instructRL converges to human-like policies that satisfy the given instructions in a proof-of-concept environment as well as the challenging Hanabi benchmark. Finally, we show that knowing the language instruction significantly boosts human-AI coordination performance in human evaluations in Hanabi. Hengyuan Hu, Dorsa Sadigh	ICML	2
2023	Long Horizon Temperature Scaling abstract Temperature scaling is a popular technique for tuning the sharpness of a model distribution. It is used extensively for sampling likely generations and calibrating model uncertainty, and even features as a controllable parameter to many large language models in deployment. However, autoregressive models rely on myopic temperature scaling that greedily optimizes the next token. To address this, we propose Long Horizon Temperature Scaling (LHTS), a novel approach for sampling from temperature-scaled joint distributions. LHTS is compatible with all likelihood-based models, and optimizes for the long-horizon likelihood of samples. We derive a temperature-dependent LHTS objective, and show that fine-tuning a model on a range of temperatures produces a single model capable of generation with a controllable long-horizon temperature parameter. We experiment with LHTS on image diffusion models and character/language autoregressive models, demonstrating its advantages over myopic temperature scaling in likelihood and sample quality, and showing improvements in accuracy of a multiple choice analogy by $10$%. Andy Shih, Dorsa Sadigh, Stefano Ermon	ICML	2
2023	Generating Language Corrections for Teaching Physical Control Tasks abstract AI assistance continues to help advance applications in education, from language learning to intelligent tutoring systems, yet current methods for providing students feedback are still quite limited. Most automatic feedback systems either provide binary correctness feedback, which may not help a student understand how to improve, or require hand-coding feedback templates, which may not generalize to new domains. This can be particularly challenging for physical control tasks, where the rich diversity in student behavior and specialized domains make it challenging to leverage general-purpose assistive tools for providing feedback. We design and build CORGI, a model trained to generate language corrections for physical control tasks, such as learning to ride a bike. CORGI takes in as input a pair of student and expert trajectories, and then generates natural language corrections to help the student improve. We collect and train CORGI over data from three diverse physical control tasks (drawing, steering, and joint movement). Through both automatic and human evaluations, we show that CORGI can (i) generate valid feedback for novel student trajectories, (ii) outperform baselines on domains with novel control dynamics, and (iii) improve student learning in an interactive drawing task. Megha Srivastava, Noah D. Goodman, Dorsa Sadigh	ICML	3
2023	Learning Tool Morphology for Contact-Rich Manipulation Tasks with Differentiable Simulation abstract When humans perform contact-rich manipulation tasks, customized tools are often necessary to simplify the task. For instance, we use various utensils for handling food, such as knives, forks and spoons. Similarly, robots may benefit from specialized tools that enable them to more easily complete a variety of tasks. We present an end-to-end framework to automatically learn tool morphology for contact-rich manipulation tasks by leveraging differentiable physics simulators. Previous work relied on manually constructed priors requiring detailed specification of a 3D object model, grasp pose and task description to facilitate the search or optimization process. Our approach only requires defining the objective with respect to task performance and enables learning a robust morphology through randomizing variations of the task. We make this optimization tractable by casting it as a continual learning problem. We demonstrate the effectiveness of our method for designing new tools in several scenarios, such as winding ropes, flipping a box and pushing peas onto a scoop in simulation. Additionally, experiments with real robots show that the tool shapes discovered by our method help them succeed in these scenarios. Mengxi Li, Rika Antonova, Dorsa Sadigh, Jeannette Bohg	ICRA	3
2023	Active Reward Learning from Online Preferences abstract Robot policies need to adapt to human preferences and/or new environments. Human experts may have the domain knowledge required to help robots achieve this adaptation. However, existing works often require costly offline re-training on human feedback, and those feedback usually need to be frequent and too complex for the humans to reliably provide. To avoid placing undue burden on human experts and allow quick adaptation in critical real-world situations, we propose designing and sparingly presenting easy-to-answer pairwise action preference queries in an online fashion. Our approach designs queries and determines when to present them to maximize the expected value derived from the queries' information. We demonstrate our approach with experiments in simulation, human user studies, and real robot experiments. In these settings, our approach outperforms baseline techniques while presenting fewer queries to human experts. Experiment videos, code and appendices are found on our website: http://tinyurl.com/online-active Vivek Myers, Erdem Biyik, Dorsa Sadigh	ICRA	3
2023	In-Mouth Robotic Bite Transfer with Visual and Haptic Sensing abstract Assistance during eating is essential for those with severe mobility issues or eating risks. However, dependence on traditional human caregivers is linked to malnutrition, weight loss, and low self-esteem. For those who require eating assistance, a semi-autonomous robotic platform can provide independence and a healthier lifestyle. We demonstrate an essential capability of this platform: safe, comfortable, and effective transfer of a bite-sized food item from a utensil directly to the inside of a person's mouth. Our system uses a force-reactive controller to safely accommodate the user's motions throughout the transfer, allowing full reactivity until bite detection then reducing reactivity in the direction of exit. Additionally, we introduce a novel dexterous wrist-like end effector capable of small, unimposing movements to reduce user discomfort. We conduct a user study with 11 participants covering 8 diverse food categories to evaluate our system end-to-end, and we find that users strongly prefer our method to a wide range of baselines. Appendices and videos are available at our website: https://tinyurl.com/btICRA. Lorenzo Shaikewitz, Yilin Wu 0003, Suneel Belkhale, Jennifer Grannen, Priya Sundaresan, Dorsa Sadigh	ICRA	6
2023	Soy: An Efficient MILP Solver for Piecewise-Affine Systems abstract Piecewise-affine (PWA) systems are widely used for modeling and control of robotics problems including modeling contact dynamics. A common approach is to encode the control problem of the PWA system as a Mixed-Integer Convex Program (MICP), which can be solved by general-purpose off-the-shelf MICP solvers. To mitigate the scalability challenge of solving these MICP problems, existing work focuses on devising efficient and strong formulations of the problems, while less effort has been spent on exploiting their specific structure to develop specialized solvers. The latter is the theme of our work. We focus on efficiently handling one-hot constraints, which are particularly relevant when encoding PWA dynamics. We have implemented our techniques in a tool, Soy, which organically integrates logical reasoning, arithmetic reasoning, and stochastic local search. For a set of PWA control benchmarks, Soy solves more problems, faster, than two state-of-the-art MICP solvers. Haoze Wu 0001, Min Wu 0011, Dorsa Sadigh, Clark W. Barrett	IROS	3
2023	Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations abstract Multimodal demonstrations provide robots with an abundance of information to make sense of the world. However, such abundance may not always lead to good performance when it comes to learning sensorimotor control policies from human demonstrations. Extraneous data modalities can lead to state over-specification, where the state contains modalities that are not only useless for decision-making but also can change data distribution across environments. State over-specification leads to issues such as the learned policy not generalizing outside of the training data distribution. In this work, we propose Masked Imitation Learning (MIL) to address state over-specification by selectively using informative modalities. Specifically, we design a masked policy network with a binary mask to block certain modalities. We develop a bi-level optimization algorithm that learns this mask to accurately filter over-specified modalities. We demonstrate empirically that MIL outperforms baseline algorithms in simulated domains and effectively recovers the environment-invariant modalities on a multimodal dataset collected on a real robot. Videos and supplemental details are at: https://tinyurl.com/masked-il Yilun Hao, Ruinan Wang, Zhangjie Cao, Yuchen Cui, Dorsa Sadigh	IROS	6
2023	Data Quality in Imitation Learning abstract In supervised learning, the question of data quality and curation has been sidelined in recent years in favor of increasingly more powerful and expressive models that can ingest internet-scale data. However, in offline learning for robotics, we simply lack internet scale data, and so high quality datasets are a necessity. This is especially true in imitation learning (IL), a sample efficient paradigm for robot learning using expert demonstrations. Policies learned through IL suffer from state distribution shift at test time due to compounding errors in action prediction, which leads to unseen states that the policy cannot recover from. Instead of designing new algorithms to address distribution shift, an alternative perspective is to develop new ways of assessing and curating datasets. There is growing evidence that the same IL algorithms can have substantially different performance across different datasets. This calls for a formalism for defining metrics of "data quality" that can further be leveraged for data curation. In this work, we take the first step toward formalizing data quality for imitation learning through the lens of distribution shift: a high quality dataset encourages the policy to stay in distribution at test time. We propose two fundamental properties that are necessary for a high quality datasets: i) action divergence: the mismatch between the expert and learned policy at certain states; and ii) transition diversity: the noise present in the system for a given state and action. We investigate the combined effect of these two key properties in imitation learning theoretically, and we empirically analyze models trained on a variety of different data sources. We show that state diversity is not always beneficial, and we demonstrate how action divergence and transition diversity interact in practice. Suneel Belkhale, Yuchen Cui, Dorsa Sadigh	NeurIPS	3
2023	Inverse Preference Learning: Preference-based RL without a Reward Function abstract Reward functions are difficult to design and often hard to align with human intent. Preference-based Reinforcement Learning (RL) algorithms address these problems by learning reward functions from human feedback. However, the majority of preference-based RL methods na\"ively combine supervised reward models with off-the-shelf RL algorithms. Contemporary approaches have sought to improve performance and query complexity by using larger and more complex reward architectures such as transformers. Instead of using highly complex architectures, we develop a new and parameter-efficient algorithm, Inverse Preference Learning (IPL), specifically designed for learning from offline preference data. Our key insight is that for a fixed policy, the $Q$-function encodes all information about the reward function, effectively making them interchangeable. Using this insight, we completely eliminate the need for a learned reward function. Our resulting algorithm is simpler and more parameter-efficient. Across a suite of continuous control and robotics benchmarks, IPL attains competitive performance compared to more complex approaches that leverage transformer-based and non-Markovian reward functions while having fewer algorithmic hyperparameters and learned network parameters. Our code is publicly released. Joey Hejna, Dorsa Sadigh	NeurIPS	2
2023	Diverse Conventions for Human-AI Collaboration abstract Conventions are crucial for strong performance in cooperative multi-agent games, because they allow players to coordinate on a shared strategy without explicit communication. Unfortunately, standard multi-agent reinforcement learning techniques, such as self-play, converge to conventions that are arbitrary and non-diverse, leading to poor generalization when interacting with new partners. In this work, we present a technique for generating diverse conventions by (1) maximizing their rewards during self-play, while (2) minimizing their rewards when playing with previously discovered conventions (cross-play), stimulating conventions to be semantically different. To ensure that learned policies act in good faith despite the adversarial optimization of cross-play, we introduce mixed-play, where an initial state is randomly generated by sampling self-play and cross-play transitions and the player learns to maximize the self-play reward from this initial state. We analyze the benefits of our technique on various multi-agent collaborative games, including Overcooked, and find that our technique can adapt to the conventions of humans, surpassing human-level performance when paired with real users. Bidipta Sarkar, Andy Shih, Dorsa Sadigh	NeurIPS	3
2023	Parallel Sampling of Diffusion Models abstract Diffusion models are powerful generative models but suffer from slow sampling, often taking 1000 sequential denoising steps for one sample. As a result, considerable efforts have been directed toward reducing the number of denoising steps, but these methods hurt sample quality. Instead of reducing the number of denoising steps (trading quality for speed), in this paper we explore an orthogonal approach: can we run the denoising steps in parallel (trading compute for speed)? In spite of the sequential nature of the denoising steps, we show that surprisingly it is possible to parallelize sampling via Picard iterations, by guessing the solution of future denoising steps and iteratively refining until convergence. With this insight, we present ParaDiGMS, a novel method to accelerate the sampling of pretrained diffusion models by denoising multiple steps in parallel. ParaDiGMS is the first diffusion sampling method that enables trading compute for speed and is even compatible with existing fast sampling techniques such as DDIM and DPMSolver. Using ParaDiGMS, we improve sampling speed by 2-4x across a range of robotics and image generation models, giving state-of-the-art sampling speeds of 0.2s on 100-step DiffusionPolicy and 14.6s on 1000-step StableDiffusion-v2 with no measurable degradation of task reward, FID score, or CLIP score. Andy Shih, Suneel Belkhale, Stefano Ermon, Dorsa Sadigh, Nima Anari	NeurIPS	4
2023	RoboCLIP: One Demonstration is Enough to Learn Robot Policies abstract Reward specification is a notoriously difficult problem in reinforcement learning, requiring extensive expert supervision to design robust reward functions. Imitation learning (IL) methods attempt to circumvent these problems by utilizing expert demonstrations instead of using an extrinsic reward function but typically require a large number of in-domain expert demonstrations. Inspired by advances in the field of Video-and-Language Models (VLMs), we present RoboCLIP, an online imitation learning method that uses a single demonstration (overcoming the large data requirement) in the form of a video demonstration or a textual description of the task to generate rewards without manual reward function design. Additionally, RoboCLIP can also utilize out-of-domain demonstrations, like videos of humans solving the task for reward generation, circumventing the need to have the same demonstration and deployment domains. RoboCLIP utilizes pretrained VLMs without any finetuning for reward generation. Reinforcement learning agents trained with RoboCLIP rewards demonstrate 2-3 times higher zero-shot performance than competing imitation learning methods on downstream robot manipulation tasks, doing so using only one video/text demonstration. Visit our website at https://sites.google.com/view/roboclip/home for experiment videos. Sumedh A. Sontakke, Jesse Zhang, Sébastien M. R. Arnold, Karl Pertsch, Erdem Biyik, Dorsa Sadigh, Chelsea Finn, Laurent Itti	NeurIPS	6
2022	Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams abstract When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of greedily doing what is best for just themselves. We would like our AI agents to effectively collaborate in a similar way by capturing a model of their partners. In this work, we propose and analyze a decentralized Multi-Armed Bandit (MAB) problem with coupled rewards as an abstraction of more general multi-agent collaboration. We demonstrate that naive extensions of single-agent optimal MAB algorithms fail when applied for decentralized bandit teams. Instead, we propose a Partner-Aware strategy for joint sequential decision-making that extends the well-known single-agent Upper Confidence Bound algorithm. We analytically show that our proposed strategy achieves logarithmic regret, and provide extensive experiments involving human-AI and human-robot collaboration to validate our theoretical findings. Our results show that the proposed partner-aware strategy outperforms other known methods, and our human subject studies suggest humans prefer to collaborate with AI agents implementing our partner-aware strategy. Erdem Biyik, Anusha Lalitha, Rajarshi Saha, Andrea J. Goldsmith, Dorsa Sadigh	AAAI	5
2022	PantheonRL: A MARL Library for Dynamic Training Interactions abstract We present PantheonRL, a multiagent reinforcement learning software package for dynamic training interactions such as round-robin, adaptive, and ad-hoc training. Our package is designed around flexible agent objects that can be easily configured to support different training interactions, and handles fully general multiagent environments with mixed rewards and n agents. Built on top of StableBaselines3, our package works directly with existing powerful deep RL algorithms. Finally, PantheonRL comes with an intuitive yet functional web user interface for configuring experiments and launching multiple asynchronous jobs. Our package can be found at https://github.com/Stanford-ILIAD/PantheonRL. Bidipta Sarkar, Aditi Talati, Andy Shih, Dorsa Sadigh	AAAI	4
2022	How do people incorporate advice from artificial agents when making physical judgments? Erik Brockbank, Justin Yang, Suvir Mirchandani, Erdem Biyik, Dorsa Sadigh, Judith E. Fan	CogSci	6
2022	APReL: A Library for Active Preference-based Reward Learning Algorithms abstract Reward learning is a fundamental problem in human-robot interaction to have robots that operate in alignment with what their human user wants. Many preference-based learning algorithms and active querying techniques have been proposed as a solution to this problem. In this paper, we present APReL, a library for active preference-based reward learning algorithms, which enable researchers and practitioners to experiment with the existing techniques and easily develop their own algorithms for various modules of the problem. APReL is available at https://github.com/Stanford-ILIAD/APReL. Erdem Biyik, Aditi Talati, Dorsa Sadigh	HRI	3
2022	Conditional Imitation Learning for Multi-Agent Games abstract While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents to adjust their strategy based on the strategies of those around them. In this work, we study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time, and we must interact with and adapt to new partners at test time. This setting is challenging because we must infer a new partner's strategy and adapt our policy to that strategy, all without knowledge of the environment reward or dynamics. We formalize this problem of conditional multi-agent imitation learning, and propose a novel approach to address the difficulties of scalability and data scarcity. Our key insight is that variations across partners in multi-agent games are often highly structured, and can be represented via a low-rank subspace. Leveraging tools from tensor decomposition, our model learns a low-rank subspace over ego and partner agent strategies, then infers and adapts to a new partner strategy by interpolating in the subspace. We experiments with a mix of collaborative tasks, including bandits, particle, and Hanabi environments. Additionally, we test our conditional policies against real human partners in a user study on the Overcooked game. Our model adapts better to new partners compared to baselines, and robustly handles diverse settings ranging from discrete/continuous actions and static/online evaluation with AI/human partners. Andy Shih, Stefano Ermon, Dorsa Sadigh	HRI	3
2022	Imitation Learning by Estimating Expertise of Demonstrators abstract Many existing imitation learning datasets are collected from multiple demonstrators, each with different expertise at different parts of the environment. Yet, standard imitation learning algorithms typically treat all demonstrators as homogeneous, regardless of their expertise, absorbing the weaknesses of any suboptimal demonstrators. In this work, we show that unsupervised learning over demonstrator expertise can lead to a consistent boost in the performance of imitation learning algorithms. We develop and optimize a joint model over a learned policy and expertise levels of the demonstrators. This enables our model to learn from the optimal behavior and filter out the suboptimal behavior of each demonstrator. Our model learns a single policy that can outperform even the best demonstrator, and can be used to estimate the expertise of any demonstrator at any state. We illustrate our findings on real-robotic continuous control tasks from Robomimic and discrete environments such as MiniGrid and chess, out-performing competing methods in 21 out of 23 settings, with an average of 7% and up to 60% improvement in terms of the final reward. Mark Beliaev, Andy Shih, Stefano Ermon, Dorsa Sadigh, Ramtin Pedarsani	ICML	4
2022	Balancing Efficiency and Comfort in Robot-Assisted Bite Transfer abstract Robot-assisted feeding in household environments is challenging because it requires robots to generate trajectories that effectively bring food items of varying shapes and sizes into the mouth while making sure the user is comfortable. Our key insight is that in order to solve this challenge, robots must balance the efficiency of feeding a food item with the comfort of each individual bite. We formalize comfort and efficiency as heuristics to incorporate in motion planning. We present an approach based on heuristics-guided bi-directional Rapidly-exploring Random Trees (h-BiRRT) that selects bite transfer trajectories of arbitrary food item geometries and shapes using our developed bite efficiency and comfort heuristics and a learned constraint model. Real-robot evaluations show that op-timizing both comfort and efficiency significantly outperforms a fixed-pose based method, and users preferred our method significantly more than that of a method that maximizes only user comfort. Videos and Appendices are found on our website: https://tinyurl.com/bticra22. Suneel Belkhale, Ethan K. Gordon, Yuxiao Chen 0006, Siddhartha S. Srinivasa, Tapomayukh Bhattacharjee, Dorsa Sadigh	ICRA	6
2022	Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction abstract Multi-agent interactions are important to model for forecasting other agents' behaviors and trajectories. At a certain time, to forecast a reasonable future trajectory, each agent needs to pay attention to the interactions with only a small group of most relevant agents instead of unnecessarily paying attention to all the other agents. However, existing attention modeling works ignore that human attention in driving does not change rapidly, and may introduce fluctuating attention across time steps. In this paper, we formulate an attention model for multi-agent interactions based on a total variation temporal smoothness prior and propose a trajectory prediction architecture that leverages the knowledge of these attended interactions. We demonstrate how the total variation attention prior along with the new sequence prediction loss terms leads to smoother attention and more sample-efficient learning of multi-agent trajectory prediction, and show its advantages in terms of prediction accuracy by comparing it with the state-of-the-art approaches on both synthetic and naturalistic driving data. We demonstrate the performance of our algorithm for trajectory prediction on the INTERACTION dataset on our website11https://sites.google.com/view/smoothness-attention. Zhangjie Cao, Erdem Biyik, Guy Rosman, Dorsa Sadigh	ICRA	4
2022	Learning from Imperfect Demonstrations via Adversarial Confidence Transfer abstract Existing learning from demonstration algorithms usually assume access to expert demonstrations. However, this assumption is limiting in many real-world applications since the collected demonstrations may be suboptimal or even consist of failure cases. We therefore study the problem of learning from imperfect demonstrations by learning a confidence predictor. Specifically, we rely on demonstrations along with their confidence values from a different correspondent environment (source environment) to learn a confidence predictor for the environment we aim to learn a policy in (target environment-where we only have unlabeled demonstrations). We learn a common latent space through adversarial distribution matching of multi-length partial trajectories to enable the transfer of confidence across source and target environments. The learned confidence reweights the demonstrations to enable learning more from informative demonstrations and discarding the irrelevant ones. Our experiments in three simulated environments and a real robot reaching task demonstrate that our approach learns a policy with the highest expected return. We show the videos of our experiments on our website. Zhangjie Cao, Dorsa Sadigh	ICRA	3
2022	Weakly Supervised Correspondence Learning abstract Correspondence learning is a fundamental problem in robotics, which aims to learn a mapping between state, action pairs of agents of different dynamics or embodiments. However, current correspondence learning methods either leverage strictly paired data-which are often difficult to collect-or learn in an unsupervised fashion from unpaired data using regularization techniques such as cycle-consistency-which suffer from severe misalignment issues. We propose a weakly supervised correspondence learning approach that trades off between strong supervision over strictly paired data and unsupervised learning with a regularizer over unpaired data. Our idea is to leverage two types of weak supervision: i) temporal ordering of states and actions to reduce the compounding error, and ii) paired abstractions, instead of paired data, to alleviate the misalignment problem and learn a more accurate correspondence. The two types of weak supervision are easy to access in real-world applications, which simultaneously reduces the high cost of annotating strictly paired data and improves the quality of the learned correspondence. We show the videos of the experiments on our website. Zhangjie Cao, Yilun Hao, Dorsa Sadigh	ICRA	4
2022	Training and Inference on Any-Order Autoregressive Models the Right Way abstract Conditional inference on arbitrary subsets of variables is a core problem in probabilistic inference with important applications such as masked language modeling and image inpainting. In recent years, the family of Any-Order Autoregressive Models (AO-ARMs) -- closely related to popular models such as BERT and XLNet -- has shown breakthrough performance in arbitrary conditional tasks across a sweeping range of domains. But, in spite of their success, in this paper we identify significant improvements to be made to previous formulations of AO-ARMs. First, we show that AO-ARMs suffer from redundancy in their probabilistic model, i.e., they define the same distribution in multiple different ways. We alleviate this redundancy by training on a smaller set of univariate conditionals that still maintains support for efficient arbitrary conditional inference. Second, we upweight the training loss for univariate conditionals that are evaluated more frequently during inference. Our method leads to improved performance with no compromises on tractability, giving state-of-the-art likelihoods in arbitrary conditional modeling on text (Text8), image (CIFAR10, ImageNet32), and continuous tabular data domains. Andy Shih, Dorsa Sadigh, Stefano Ermon	NeurIPS	2
2022	Assistive Teaching of Motor Control Tasks to Humans abstract Recent works on shared autonomy and assistive-AI technologies, such as assistive robotic teleoperation, seek to model and help human users with limited ability in a fixed task. However, these approaches often fail to account for humans' ability to adapt and eventually learn how to execute a control task themselves. Furthermore, in applications where it may be desirable for a human to intervene, these methods may have inhibited their ability to learn how to succeed with full self-control. In this paper, we focus on the problem of assistive teaching of motor control tasks such as parking a car or landing an aircraft. Despite their ubiquitous role in humans' daily activities and occupations, motor tasks are rarely taught in a uniform way due to their high complexity and variance. We propose an AI-assisted teaching algorithm that leverages skill discovery methods from reinforcement learning (RL) literature to (i) break down any motor control task into teachable skills, (ii) construct novel drill sequences, and (iii) individualize curricula to students with different capabilities. Through an extensive mix of synthetic and user studies on two motor control tasks - parking a car with a joystick and writing characters from the Balinese alphabet - we show that assisted teaching with skills improve student performance by around 40% compared to practicing full trajectories without skills, and practicing with individualized drills can result in up to 25% further improvement. Megha Srivastava, Erdem Biyik, Suvir Mirchandani, Noah D. Goodman, Dorsa Sadigh	NeurIPS	5
2022	Social Coordination and Altruism in Autonomous Driving abstract Despite the advances in the autonomous driving domain, autonomous vehicles (AVs) are still inefficient and limited in terms of cooperating with each other or coordinating with vehicles operated by humans. A group of autonomous and human-driven vehicles (HVs) which work together to optimize an altruistic social utility can co-exist seamlessly and assure safety and efficiency on the road. Achieving this mission without explicit coordination among agents is challenging, mainly due to the difficulty of predicting the behavior of humans with heterogeneous preferences in mixed-autonomy environments. Formally, we model an AV’s maneuver planning in mixed-autonomy traffic as a partially-observable stochastic game and attempt to derive optimal policies that lead to socially-desirable outcomes using a multi-agent reinforcement learning framework (MARL), and propose a semi-sequential multi-agent training and policy dissemination algorithm for our MARL problem. We introduce a quantitative representation of the AVs’ social preferences and design a distributed reward structure that induces altruism into their decision-making process. Altruistic AVs are able to form alliances, guide the traffic, and affect the behavior of the HVs to handle competitive driving scenarios. We compare egoistic AVs to our altruistic autonomous agents in a highway merging setting and demonstrate the emerging behaviors that lead to improvement in the number of successful merges and the overall traffic flow and safety. Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh, Ramtin Pedarsani, Yaser P. Fallah	IEEE Trans. Intell. Transp. Syst.	3
2021	Open-domain clarification question generation without question examples abstract An overarching goal of natural language processing is to enable machines to communicate seamlessly with humans.However, natural language can be ambiguous or unclear.In cases of uncertainty, humans engage in an interactive process known as repair: asking questions and seeking clarification until their uncertainty is resolved.We propose a framework for building a visually grounded questionasking model capable of producing polar (yesno) clarification questions to resolve misunderstandings in dialogue.Our model uses an expected information gain objective to derive informative questions from an off-the-shelf image captioner without requiring any supervised question-answer data.We demonstrate our model's ability to pose questions that improve communicative success in a goal-oriented 20 questions game with synthetic and human answerers. Julia White 0001, Gabriel Poesia, Robert D. Hawkins, Dorsa Sadigh, Noah D. Goodman	EMNLP (1)	4
2021	On the Critical Role of Conventions in Adaptive Human-AI Collaboration Andy Shih, Arjun Sawhney, Jovana Kondic, Stefano Ermon, Dorsa Sadigh	ICLR	5
2021	Targeted Data Acquisition for Evolving Negotiation Agents abstract Successful negotiators must learn how to balance optimizing for self-interest and cooperation. Yet current artificial negotiation agents often heavily depend on the quality of the static datasets they were trained on, limiting their capacity to fashion an adaptive response balancing self-interest and cooperation. For this reason, we find that these agents can achieve either high utility or cooperation, but not both. To address this, we introduce a targeted data acquisition framework where we guide the exploration of a reinforcement learning agent using annotations from an expert oracle. The guided exploration incentivizes the learning agent to go beyond its static dataset and develop new negotiation strategies. We show that this enables our agents to obtain higher-reward and more Pareto-optimal solutions when negotiating with both simulated and human partners compared to standard supervised learning and reinforcement learning methods. This trend additionally holds when comparing agents using our targeted data acquisition framework to variants of agents trained with a mix of supervised learning and reinforcement learning, or to agents using tailored reward functions that explicitly optimize for utility and Pareto-optimality. Minae Kwon, Siddharth Karamcheti, Mariano-Florentino Cuellar, Dorsa Sadigh	ICML	4
2021	Learning Human Objectives from Sequences of Physical Corrections abstract When personal, assistive, and interactive robots make mistakes, humans naturally and intuitively correct those mistakes through physical interaction. In simple situations, one correction is sufficient to convey what the human wants. But when humans are working with multiple robots or the robot is performing an intricate task often the human must make several corrections to fix the robot’s behavior. Prior research assumes each of these physical corrections are independent events, and learns from them one-at-a-time. However, this misses out on crucial information: each of these interactions are interconnected, and may only make sense if viewed together. Alternatively, other work reasons over the final trajectory produced by all of the human’s corrections. But this method must wait until the end of the task to learn from corrections, as opposed to inferring from the corrections in an online fashion. In this paper we formalize an approach for learning from sequences of physical corrections during the current task. To do this we introduce an auxiliary reward that captures the human’s trade-off between making corrections which improve the robot’s immediate reward and long-term performance. We evaluate the resulting algorithm in remote and in-person human-robot experiments, and compare to both independent and final baselines. Our results indicate that users are best able to convey their objective when the robot reasons over their sequence of corrections. Mengxi Li, Alper Canberk, Dylan P. Losey, Dorsa Sadigh	ICRA	4
2021	ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes abstract Characterizing what types of exoskeleton gaits are comfortable for users, and understanding the science of walking more generally, require recovering a user’s utility landscape. Learning these landscapes is challenging, as walking trajectories are defined by numerous gait parameters, data collection from human trials is expensive, and user safety and comfort must be ensured. This work proposes the Region of Interest Active Learning (ROIAL) framework, which actively learns each user’s underlying utility function over a region of interest that ensures safety and comfort. ROIAL learns from ordinal and preference feedback, which are more reliable feedback mechanisms than absolute numerical scores. The algorithm’s performance is evaluated both in simulation and experimentally for three non-disabled subjects walking inside of a lower-body exoskeleton. ROIAL learns Bayesian posteriors that predict each exoskeleton user’s utility landscape across four exoskeleton gait parameters. The algorithm discovers both commonalities and discrepancies across users’ gait preferences and identifies the gait parameters that most influenced user feedback. These results demonstrate the feasibility of recovering gait utility landscapes from limited human trials. Maegan Tucker, Erdem Biyik, Ellen R. Novoseller, Joel W. Burdick, Yanan Sui, Dorsa Sadigh, Yisong Yue, Aaron D. Ames	ICRA	7
2021	Emergent Prosociality in Multi-Agent Games Through Gifting abstract Coordination is often critical to forming prosocial behaviors -- behaviors that increase the overall sum of rewards received by all agents in a multi-agent game. However, state of the art reinforcement learning algorithms often suffer from converging to socially less desirable equilibria when multiple equilibria exist. Previous works address this challenge with explicit reward shaping, which requires the strong assumption that agents can be forced to be prosocial. We propose using a less restrictive peer-rewarding mechanism, gifting, that guides the agents toward more socially desirable equilibria while allowing agents to remain selfish and decentralized. Gifting allows each agent to give some of their reward to other agents. We employ a theoretical framework that captures the benefit of gifting in converging to the prosocial equilibrium by characterizing the equilibria's basins of attraction in a dynamical system. With gifting, we demonstrate increased convergence of high risk, general-sum coordination games to the prosocial equilibrium both via numerical analysis and experiments. Woodrow Z. Wang, Mark Beliaev, Erdem Biyik, Daniel A. Lazar, Ramtin Pedarsani, Dorsa Sadigh	IJCAI	6
2021	Cooperative Autonomous Vehicles that Sympathize with Human Drivers abstract Widespread adoption of autonomous vehicles will not become a reality until solutions are developed that enable these intelligent agents to co-exist with humans. This includes safely and efficiently interacting with human-driven vehicles, especially in both conflictive and competitive scenarios. We build up on the prior work on socially-aware navigation and borrow the concept of social value orientation from psychology —that formalizes how much importance a person allocates to the welfare of others— in order to induce altruistic behavior in autonomous driving. In contrast with existing works that explicitly model the behavior of human drivers and rely on their expected response to create opportunities for cooperation, our Sympathetic Cooperative Driving (SymCoDrive) paradigm trains altruistic agents that realize safe and smooth traffic flow in competitive driving scenarios only from experiential learning and without any explicit coordination. We demonstrate a significant improvement in both safety and traffic-level metrics as a result of this altruistic behavior and importantly conclude that the level of altruism in agents requires proper tuning as agents that are too altruistic also lead to sub-optimal traffic flow. The code and supplementary material are available at: https://symcodrive.toghi.net/ Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh, Ramtin Pedarsani, Yaser P. Fallah	IROS	3
2021	ELLA: Exploration through Learned Language Abstraction abstract Building agents capable of understanding language instructions is critical to effective and robust human-AI collaboration. Recent work focuses on training these agents via reinforcement learning in environments with synthetic language; however, instructions often define long-horizon, sparse-reward tasks, and learning policies requires many episodes of experience. We introduce ELLA: Exploration through Learned Language Abstraction, a reward shaping approach geared towards boosting sample efficiency in sparse reward environments by correlating high-level instructions with simpler low-level constituents. ELLA has two key elements: 1) A termination classifier that identifies when agents complete low-level instructions, and 2) A relevance classifier that correlates low-level instructions with success on high-level tasks. We learn the termination classifier offline from pairs of instructions and terminal states. Notably, in departure from prior work in language and abstraction, we learn the relevance classifier online, without relying on an explicit decomposition of high-level instructions to low-level instructions. On a suite of complex BabyAI environments with varying instruction complexities and reward sparsity, ELLA shows gains in sample efficiency relative to language-based shaping and traditional RL methods. Suvir Mirchandani, Siddharth Karamcheti, Dorsa Sadigh	NeurIPS	3
2021	HyperSPNs: Compact and Expressive Probabilistic Circuits abstract Probabilistic circuits (PCs) are a family of generative models which allows for the computation of exact likelihoods and marginals of its probability distributions. PCs are both expressive and tractable, and serve as popular choices for discrete density estimation tasks. However, large PCs are susceptible to overfitting, and only a few regularization strategies (e.g., dropout, weight-decay) have been explored. We propose HyperSPNs: a new paradigm of generating the mixture weights of large PCs using a small-scale neural network. Our framework can be viewed as a soft weight-sharing strategy, which combines the greater expressiveness of large models with the better generalization and memory-footprint properties of small models. We show the merits of our regularization strategy on two state-of-the-art PC families introduced in recent literature -- RAT-SPNs and EiNETs -- and demonstrate generalization improvements in both models on a suite of density estimation benchmarks in both discrete and continuous domains. Andy Shih, Dorsa Sadigh, Stefano Ermon	NeurIPS	2
2021	Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality abstract Most existing imitation learning approaches assume the demonstrations are drawn from experts who are optimal, but relaxing this assumption enables us to use a wider range of data. Standard imitation learning may learn a suboptimal policy from demonstrations with varying optimality. Prior works use confidence scores or rankings to capture beneficial information from demonstrations with varying optimality, but they suffer from many limitations, e.g., manually annotated confidence scores or high average optimality of demonstrations. In this paper, we propose a general framework to learn from demonstrations with varying optimality that jointly learns the confidence score and a well-performing policy. Our approach, Confidence-Aware Imitation Learning (CAIL) learns a well-performing policy from confidence-reweighted demonstrations, while using an outer loss to track the performance of our model and to learn the confidence. We provide theoretical guarantees on the convergence of CAIL and evaluate its performance in both simulated and real robot experiments.Our results show that CAIL significantly outperforms other imitation learning methods from demonstrations with varying optimality. We further show that even without access to any optimal demonstrations, CAIL can still learn a successful policy, and outperforms prior work. Songyuan Zhang, Zhangjie Cao, Dorsa Sadigh, Yanan Sui	NeurIPS	3
2020	Continual Adaptation for Efficient Machine Communication abstract To communicate with new partners in new contexts, humans rapidly form new linguistic conventions.Recent neural language models are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do.We introduce an interactive repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time.We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners. Robert D. Hawkins, Minae Kwon, Dorsa Sadigh, Noah D. Goodman	CoNLL	3
2020	When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans abstract In order to collaborate safely and efficiently, robots need to anticipate how their human partners will behave. Some of today's robots model humans as if they were also robots, and assume users are always optimal. Other robots account for human limitations, and relax this assumption so that the human is noisily rational. Both of these models make sense when the human receives deterministic rewards: i.e., gaining either $100 or $130 with certainty. But in real-world scenarios, rewards are rarely deterministic. Instead, we must make choices subject to risk and uncertainty-and in these settings, humans exhibit a cognitive bias towards suboptimal behavior. For example, when deciding between gaining $100 with certainty or $130 only 80% of the time, people tend to make the risk-averse choice-even though it leads to a lower expected gain! In this paper, we adopt a well-known Risk-Aware human model from behavioral economics called Cumulative Prospect Theory and enable robots to leverage this model during human-robot interaction (HRI). In our user studies, we offer supporting evidence that the Risk-Aware model more accurately predicts suboptimal human behavior. We find that this increased modeling accuracy results in safer and more efficient human-robot collaboration. Overall, we extend existing rational human models so that collaborative robots can anticipate and plan around suboptimal human behavior during HRI. Minae Kwon, Erdem Biyik, Aditi Talati, Karan Bhasin, Dylan P. Losey, Dorsa Sadigh	HRI	6
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	5
2020	Learning User-Preferred Mappings for Intuitive Robot Control abstract When humans control drones, cars, and robots, we often have some preconceived notion of how our inputs should make the system behave. Existing approaches to teleoperation typically assume a one-size-fits-all approach, where the designers pre-define a mapping between human inputs and robot actions, and every user must adapt to this mapping over repeated interactions. Instead, we propose a personalized method for learning the human's preferred or preconceived mapping from a few robot queries. Given a robot controller, we identify an alignment model that transforms the human's inputs so that the controller's output matches their expectations. We make this approach data-efficient by recognizing that human mappings have strong priors: we expect the input space to be proportional, reversable, and consistent. Incorporating these priors ensures that the robot learns an intuitive mapping from few examples. We test our learning approach in robot manipulation tasks inspired by assistive settings, where each user has different personal preferences and physical capabilities for teleoperating the robot arm. Our simulated and experimental results suggest that learning the mapping between inputs and robot actions improves objective and subjective performance when compared to manually defined alignments or learned alignments without intuitive priors. The supplementary video showing these user studies can be found at: https://youtu.be/rKHka0_48-Q. Mengxi Li, Dylan P. Losey, Jeannette Bohg, Dorsa Sadigh	IROS	4
2020	Multi-Agent Safe Planning with Gaussian Processes abstract Multi-agent safe systems have become an increasingly important area of study as we can now easily have multiple AI-powered systems operating together. In such settings, we need to ensure the safety of not only each individual agent, but also the overall system. In this paper, we introduce a novel multi-agent safe learning algorithm that enables decentralized safe navigation when there are multiple different agents in the environment. This algorithm makes mild assumptions about other agents and is trained in a decentralized fashion, i.e. with very little prior knowledge about other agents' policies. Experiments show our algorithm performs well with the robots running other algorithms when optimizing various objectives. Zheqing Zhu, Erdem Biyik, Dorsa Sadigh	IROS	3
2020	Efficient and Trustworthy Social Navigation via Explicit and Implicit Robot-Human Communication abstract In this article, we present a planning framework that uses a combination of implicit (robot motion) and explicit (visual/audio/haptic feedback) communication during mobile robot navigation. First, we developed a model that approximates both continuous movements and discrete behavior modes in human navigation, considering the effects of implicit and explicit communication on human decision-making. The model approximates the human as an optimal agent, with a reward function obtained through inverse reinforcement learning. Second, a planner uses this model to generate communicative actions that maximize the robot's transparency and efficiency. We implemented the planner on a mobile robot, using a wearable haptic device for explicit communication. In a user study of an indoor human-robot pair orthogonal crossing situation, the robot is able to actively communicate its intent to users in order to avoid collisions and facilitate efficient trajectories. Results show that the planner generated plans that are easier to understand, reduce users` effort, and increase users' trust of the robot, compared to simply performing collision avoidance. The key contribution of this article is the integration and analysis of explicit communication (together with implicit communication) for social navigation. Yuhang Che, Allison M. Okamura, Dorsa Sadigh	IEEE Trans. Robotics	3
2019	Safe and Interactive Autonomy: A Journey Starting from Formal Methods (Keynote) abstract Todays society is rapidly advancing towards autonomous systems that interact and collaborate with humans, e.g., semiautonomous vehicles interacting with drivers and pedestrians, medical robots used in collaboration with doctors, or service robots interacting with their users in smart homes. With the emergence of autonomous systems in our every day lives, we need to design algorithms and tools that enable safe and seamless interactions with people. In this talk, I will start with my journey in providing safety for human-robot systems by discussing a spectrum of views on safe autonomous systems including a formal methods perspective for synthesizing provably correct controllers, a robust control approach, and more recent advances in safe learning and verification. I will then discuss one of the main challenges of safety of human-robot systems, i.e., studying how robots influence humans actions in one-on-one or group settings. This is usually overlooked by assuming humans act as external disturbances just like moving obstacles, or assuming that automation can always help societies without actually considering how humans can be impacted. I will talk about our recent work in building computational models of human behavior from expert demonstrations and preferences in interaction with autonomous systems and challenges it introduces for safety and robustness verification. Dorsa Sadigh	FMCAD	1
2019	Hierarchical Game-Theoretic Planning for Autonomous Vehicles abstract The actions of an autonomous vehicle on the road affect and are affected by those of other drivers, whether overtaking, negotiating a merge, or avoiding an accident. This mutual dependence, best captured by dynamic game theory, creates a strong coupling between the vehicle's planning and its predictions of other drivers' behavior, and constitutes an open problem with direct implications on the safety and viability of autonomous driving technology. Unfortunately, dynamic games are too computationally demanding to meet the real-time constraints of autonomous driving in its continuous state and action space. In this paper, we introduce a novel game-theoretic trajectory planning algorithm for autonomous driving, that enables real-time performance by hierarchically decomposing the underlying dynamic game into a long-horizon “strategic” game with simplified dynamics and full information structure, and a short-horizon “tactical” game with full dynamics and a simplified information structure. The value of the strategic game is used to guide the tactical planning, implicitly extending the planning horizon, pushing the local trajectory optimization closer to global solutions, and, most importantly, quantitatively accounting for the autonomous vehicle and the human driver's ability and incentives to influence each other. In addition, our approach admits non-deterministic models of human decision-making, rather than relying on perfectly rational predictions. Our results showcase richer, safer, and more effective autonomous behavior in comparison to existing techniques. Jaime Fernández Fisac, Eli Bronstein, Elis Stefansson, Dorsa Sadigh, S. Shankar Sastry, Anca D. Dragan	ICRA	4
2019	Deep Local Trajectory Replanning and Control for Robot Navigation abstract We present a navigation system that combines ideas from hierarchical planning and machine learning. The system uses a traditional global planner to compute optimal paths towards a goal, and a deep local trajectory planner and velocity controller to compute motion commands. The latter components of the system adjust the behavior of the robot through attention mechanisms such that it moves towards the goal, avoids obstacles, and respects the space of nearby pedestrians. Both the structure of the proposed deep models and the use of attention mechanisms make the system's execution interpretable. Our simulation experiments suggest that the proposed architecture outperforms baselines that try to map global plan information and sensor data directly to velocity commands. In comparison to a hand-designed traditional navigation system, the proposed approach showed more consistent performance. Ashwini Pokle, Roberto Martin Martin, Patrick Goebel, Vincent Chow, Hans M. Ewald, Zhenkai Wang, Amir Sadeghian, Dorsa Sadigh, Silvio Savarese, Marynel Vázquez	ICRA	9
2019	Active Learning of Reward Dynamics from Hierarchical Queries abstract Enabling robots to act according to human preferences across diverse environments is a crucial task, extensively studied by both roboticists and machine learning researchers. To achieve it, human preferences are often encoded by a reward function which the robot optimizes for. This reward function is generally static in the sense that it does not vary with time or the interactions. Unfortunately, such static reward functions do not always adequately capture human preferences, especially, in non-stationary environments: Human preferences change in response to the emergent behaviors of the other agents in the environment. In this work, we propose learning reward dynamics that can adapt in non-stationary environments with several interacting agents. We define reward dynamics as a tuple of reward functions, one for each mode of interaction, and mode-utility functions governing transitions between the modes. Reward dynamics thereby encodes not only different human preferences but also how the preferences change. Our contribution is in the way we adapt preference-based learning into a hierarchical approach that aims at learning not only reward functions but also how they evolve based on interactions. We derive a probabilistic observation model of how people will respond to the hierarchical queries. Our algorithm leverages this model to actively select hierarchical queries that will maximize the volume removed from a continuous hypothesis space of reward dynamics. We empirically demonstrate reward dynamics can match human preferences accurately. Chandrayee Basu, Erdem Biyik, Zhixun He, Mukesh Singhal, Dorsa Sadigh	IROS	5
2019	Robots that Take Advantage of Human Trust abstract Humans often assume that robots are rational. We believe robots take optimal actions given their objective; hence, when we are uncertain about what the robot's objective is, we interpret the robot's actions as optimal with respect to our estimate of its objective. This approach makes sense when robots straightforwardly optimize their objective, and enables humans to learn what the robot is trying to achieve. However, our insight is that-when robots are aware that humans learn by trusting that the robot actions are rational-intelligent robots do not act as the human expects; instead, they take advantage of the human's trust, and exploit this trust to more efficiently optimize their own objective. In this paper, we formally model instances of human-robot interaction (HRI) where the human does not know the robot's objective using a two-player game. We formulate different ways in which the robot can model the uncertain human, and compare solutions of this game when the robot has conservative, optimistic, rational, and trusting human models. In an offline linear-quadratic case study and a real-time user study, we show that trusting human models can naturally lead to communicative robot behavior, which influences end-users and increases their involvement. Dylan P. Losey, Dorsa Sadigh	IROS	2
2018	Multi-Agent Generative Adversarial Imitation Learning abstract Imitation learning algorithms can be used to learn a policy from expert demonstrations without access to a reward signal. However, most existing approaches are not applicable in multi-agent settings due to the existence of multiple (Nash) equilibria and non-stationary environments. We propose a new framework for multi-agent imitation learning for general Markov games, where we build upon a generalized notion of inverse reinforcement learning. We further introduce a practical multi-agent actor-critic algorithm with good empirical performance. Our method can be used to imitate complex behaviors in high-dimensional environments with multiple cooperative or competing agents. Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon	NeurIPS	3
2018	Altruistic Autonomy: Beating Congestion on Shared Roads Erdem Biyik, Daniel A. Lazar, Ramtin Pedarsani, Dorsa Sadigh	WAFR	4
2018	Safe Autonomy Under Perception Uncertainty Using Chance-Constrained Temporal Logic Susmit Jha, Vasumathi Raman, Dorsa Sadigh, Sanjit A. Seshia	J. Autom. Reason.	3
2016	Diagnosis and Repair for Synthesis from Signal Temporal Logic Specifications abstract We address the problem of diagnosing and repairing specifications for hybrid systems, formalized in signal temporal logic (STL). Our focus is on automatic synthesis of controllers from specifications using model predictive control. We build on recent approaches that reduce the controller synthesis problem to solving one or more mixed integer linear programs (MILPs), where infeasibility of an MILP usually indicates unrealizability of the controller synthesis problem. Given an infeasible STL synthesis problem, we present algorithms that provide feedback on the reasons for unrealizability, and suggestions for making it realizable. Our algorithms are sound and complete relative to the synthesis algorithm, i.e., they provide a diagnosis that makes the synthesis problem infeasible, and always terminate with a non-trivial specification that is feasible using the chosen synthesis method, when such a solution exists. We demonstrate the effectiveness of our approach on controller synthesis for various cyber-physical systems, including an autonomous driving application and an aircraft electric power system. Shromona Ghosh, Dorsa Sadigh, Pierluigi Nuzzo 0002, Vasumathi Raman, Alexandre Donzé, Alberto L. Sangiovanni-Vincentelli, S. Shankar Sastry, Sanjit A. Seshia	HSCC	2
2016	Information gathering actions over human internal state abstract Much of estimation of human internal state (goal, intentions, activities, preferences, etc.) is passive: an algorithm observes human actions and updates its estimate of human state. In this work, we embrace the fact that robot actions affect what humans do, and leverage it to improve state estimation. We enable robots to do active information gathering, by planning actions that probe the user in order to clarify their internal state. For instance, an autonomous car will plan to nudge into a human driver's lane to test their driving style. Results in simulation and in a user study suggest that active information gathering significantly outperforms passive state estimation. Dorsa Sadigh, S. Shankar Sastry, Sanjit A. Seshia, Anca D. Dragan	IROS	1
2015	Formal methods for semi-autonomous driving abstract We give an overview of the main challenges in the specification, design, and verification of human cyber-physical systems, with a special focus on semi-autonomous vehicles. We identify unique characteristics of formal modeling, specification, verification and synthesis in this domain. Some initial results and design principles are presented along with directions for future work. Sanjit A. Seshia, Dorsa Sadigh, S. Shankar Sastry	DAC	2
2015	Reactive synthesis from signal temporal logic specifications abstract We present a counterexample-guided inductive synthesis approach to controller synthesis for cyber-physical systems subject to signal temporal logic (STL) specifications, operating in potentially adversarial nondeterministic environments. We encode STL specifications as mixed integer-linear constraints on the variables of a discrete-time model of the system and environment dynamics, and solve a series of optimization problems to yield a satisfying control sequence. We demonstrate how the scheme can be used in a receding horizon fashion to fulfill properties over unbounded horizons, and present experimental results for reactive controller synthesis for case studies in building climate control and autonomous driving. Vasumathi Raman, Alexandre Donzé, Dorsa Sadigh, Richard M. Murray, Sanjit A. Seshia	HSCC	3
2014	Synthesis for Human-in-the-Loop Control Systems Wenchao Li 0001, Dorsa Sadigh, S. Shankar Sastry, Sanjit A. Seshia	TACAS	2
2011	Timing analysis of interrupt-driven programs under context bounds Jonathan Kotker, Dorsa Sadigh, Sanjit A. Seshia	FMCAD	2