Ashwin Balakrishna

EDBT 2026 Demo / reviewers in the wild / expert

dblp:218/5246 · DBLP profile ↗

← Back

15ranked-venue papers

0as first author

12since 2021 · last 2025

0000-0002-3508-7850ORCID · corroborated

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

Artificial intelligence and machine learning · 15 · 12 since 2021Systems, architecture and hardware · 11 · 8 since 2021

Year	Publication	Venue	Position
2025	Robo-DM: Data Management for Large Robot Datasets abstract Recent results suggest that very large datasets of teleoperated robot demonstrations can be used to train transformer-based models that have the potential to generalize to new scenes, robots, and tasks. However, curating, distributing, and loading large datasets of robot trajectories, which typically consist of video, textual, and numerical modalities - including streams from multiple cameras - remains challenging. We propose Robo-DM, an efficient open-source cloud-based data management toolkit for collecting, sharing, and learning with robot data. With Robo-DM, robot datasets are stored in a self-contained format with Extensible Binary Meta Language (EBML). Robo-DM can significantly reduce the size of robot trajectory data, transfer costs, and data load time during training. Compared to the RLDS format used in OXE datasets, Robo-DM's compression saves space by up to 70x (lossy) and 3.5x (lossless). Robo-DM also accelerates data retrieval by load-balancing video decoding with memory-mapped decoding caches. Compared to LeRobot, a framework that also uses lossy video compression, Robo-DM is up to 50x faster when decoding sequentially. We physically evaluate a model trained by Robo-DM with lossy compression, a pick-and-place task, and In-Context Robot Transformer. Robo-DM uses 75x compression of the original dataset and does not suffer reduction in downstream task accuracy. Code and evaluation scripts can be found on website https://github.com/BerkeleyAutomation/fog_x. Kaiyuan Chen 0001, Letian Fu, Yunliang Chen 0001, Kush Hari, Ashwin Balakrishna, Ted Xiao, Pannag R. Sanketi, John Kubiatowicz, Kenneth Y. Goldberg	ICRA	8
2025	GHIL-Glue: Hierarchical Control with Filtered Subgoal Images abstract Image and video generative models that are pretrained on Internet-scale data can greatly increase the generalization capacity of robot learning systems. These models can function as high-level planners, generating intermediate sub-goals for low-level goal-conditioned policies to reach. However, the performance of these systems can be greatly bottlenecked by the interface between generative models and low-level controllers. For example, generative models may predict photo-realistic yet physically infeasible frames that confuse low-level policies. Low-level policies may also be sensitive to subtle visual artifacts in generated goal images. This paper addresses these two facets of generalization, providing an interface to effectively “glue together” language-conditioned image or video prediction models with low-level goal-conditioned policies. Our method, Generative Hierarchical Imitation Learning-Glue (GHIL-Glue), filters out subgoals that do not lead to task progress and improves the robustness of goal-conditioned policies to generated subgoals with harmful visual artifacts. We find in extensive experiments in both simulated and real environments that GHIL-Glue achieves a 25% improvement across several hierarchical models that leverage generative subgoals, achieving a new state-of-the-art on the CALVIN simulation benchmark for policies using observations from a single RGB camera. GHIL-Glue also outperforms other generalist robot policies across 3/4 language-conditioned manipulation tasks testing zero-shot generalization in physical experiments. Code, model checkpoints, videos, and supplementary materials can be found at https://ghil-glue.github.io. Kyle Hatch, Ashwin Balakrishna, Oier Mees, Suraj Nair 0003, Seohong Park, Blake Wulfe, Masha Itkina, Benjamin Eysenbach, Sergey Levine, Thomas Kollar, Benjamin Burchfiel	ICRA	2
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	3
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	28
2024	Language-Embedded Gaussian Splats (LEGS): Incrementally Building Room-Scale Representations with a Mobile Robot abstract Building semantic 3D maps is valuable for searching for objects of interest in offices, warehouses, stores, and homes. We present a mapping system that incrementally builds a Language-Embedded Gaussian Splat (LEGS): a detailed 3D scene representation that encodes both appearance and semantics in a unified representation. LEGS is trained online as a robot traverses its environment to enable localization of open-vocabulary object queries. We evaluate LEGS on 4 room-scale scenes where we query for objects in the scene to assess how LEGS can capture semantic meaning. We compare LEGS to LERF [1] and find that while both systems have comparable object query success rates, LEGS trains over 3.5x faster than LERF. Results suggest that a multi-camera setup and incremental bundle adjustment can boost visual reconstruction quality in constrained robot trajectories, and suggest LEGS can localize open-vocabulary and long-tail object queries with up to 66% accuracy. See project website at: berkeleyautomation.github.io/LEGS Justin Yu, Kush Hari, Kishore Srinivas, Karim El-Refai, Adam Rashid, Chung Min Kim, Justin Kerr, Richard Cheng, Muhammad Zubair Irshad, Ashwin Balakrishna, Thomas Kollar, Kenneth Y. Goldberg	IROS	10
2024	MANIP: A Modular Architecture for Integrating Interactive Perception for Robot Manipulation abstract We propose a modular systems architecture, MANIP, that can facilitate the design and development of robot manipulation systems by systematically combining learned subpolicies with well-established procedural algorithmic primitives such as Inverse Kinematics, Kalman Filters, RANSAC outlier rejection, PID modules, etc. (aka "Good Old Fashioned Engineering (GOFE)"). The MANIP architecture grew from our lab’s experience developing robot systems for folding clothes, routing cables, and untangling knots. To address failure modes, MANIP can facilitate inclusion of "interactive perception" subpolicies that execute robot actions to modify system state to bring the system into alignment with the training distribution and / or to disambiguate system state when system state confidence is low. We demonstrate how MANIP can be applied with 3 case studies and then describe a detailed case study in cable tracing with experiments that suggest MANIP can improve performance by up to 88%. Code and details are available at: https://berkeleyautomation.github.io/MANIP/ Justin Yu, Tara Sadjadpour, Abigail O'Neill, Mehdi Khfifi, Yunliang Chen 0001, Richard Cheng, Muhammad Zubair Irshad, Ashwin Balakrishna, Thomas Kollar, Kenneth Y. Goldberg	IROS	8
2022	LEGS: Learning Efficient Grasp Sets for Exploratory Grasping abstract While deep learning has enabled significant progress in designing general purpose robot grasping systems, there remain objects which still pose challenges for these systems. Recent work on Exploratory Grasping has formalized the problem of systematically exploring grasps on these adversarial objects and explored a multi-armed bandit model for identifying high-quality grasps on each object stable pose. However, these systems are still limited to exploring a small number or grasps on each object. We present Learned Efficient Grasp Sets (LEGS), an algorithm that efficiently explores thousands of possible grasps by maintaining small active sets of promising grasps and determining when it can stop exploring the object with high confidence. Experiments suggest that LEGS can identify a high-quality grasp more efficiently than prior algorithms which do not use active sets. In simulation experiments, we measure the gap between the success probability of the best grasp identified by LEGS, baselines, and the most-robust grasp (verified ground truth). After 3000 exploration steps, LEGS outperforms baseline algorithms on 10/14 and 25/39 objects on the Dex-Net Adversarial and EGAD! datasets respectively. We then evaluate LEGS in physical experiments; trials on 3 challenging objects suggest that LEGS converges to high-performing grasps significantly faster than baselines. See https://sites.google.com/view/LEGS-exp-grasping for supplemental material and videos. Letian Fu, Michael Danielczuk, Ashwin Balakrishna, Daniel S. Brown, Jeffrey Ichnowski, Eugen Solowjow, Kenneth Y. Goldberg	ICRA	3
2022	Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations abstract Providing densely shaped reward functions for RL algorithms is often exceedingly challenging, motivating the development of RL algorithms that can learn from easier-to-specify sparse reward functions. This sparsity poses new exploration challenges. One common way to address this problem is using demonstrations to provide initial signal about regions of the state space with high rewards. However, prior RL from demonstrations algorithms introduce significant complexity and many hyperparameters, making them hard to implement and tune. We introduce Monte Carlo Actor-Critic (MCAC), a parameter free modification to standard actor-critic algorithms which initializes the replay buffer with demonstrations and computes a modified $Q$-value by taking the maximum of the standard temporal distance (TD) target and a Monte Carlo estimate of the reward-to-go. This encourages exploration in the neighborhood of high-performing trajectories by encouraging high $Q$-values in corresponding regions of the state space. Experiments across $5$ continuous control domains suggest that MCAC can be used to significantly increase learning efficiency across $6$ commonly used RL and RL-from-demonstrations algorithms. See https://sites.google.com/view/mcac-rl for code and supplementary material. Albert Wilcox, Ashwin Balakrishna, Jules Dedieu, Wyame Benslimane, Daniel S. Brown, Kenneth Y. Goldberg	NeurIPS	2
2021	Policy Gradient Bayesian Robust Optimization for Imitation Learning abstract The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human feedback, leaving agents with uncertainty over what the true reward function is. While most policy optimization approaches handle this uncertainty by optimizing for expected performance, many applications demand risk-averse behavior. We derive a novel policy gradient-style robust optimization approach, PG-BROIL, that optimizes a soft-robust objective that balances expected performance and risk. To the best of our knowledge, PG-BROIL is the first policy optimization algorithm robust to a distribution of reward hypotheses which can scale to continuous MDPs. Results suggest that PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse and outperforms state-of-the-art imitation learning algorithms when learning from ambiguous demonstrations by hedging against uncertainty, rather than seeking to uniquely identify the demonstrator’s reward function. Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Kenneth Y. Goldberg	ICML	5
2021	Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabrics abstract Robotic fabric manipulation is challenging due to the infinite dimensional configuration space, self-occlusion, and complex dynamics of fabrics. There has been significant prior work on learning policies for specific fabric manipulation tasks, but comparatively less focus on algorithms which can perform many different tasks. We take a step towards this goal by learning point-pair correspondences across different fabric configurations in simulation. Then, given a single demonstration of a new task from an initial fabric configuration, these correspondences can be used to compute geometrically equivalent actions in a new fabric configuration. This makes it possible to define policies to robustly imitate a broad set of multi-step fabric smoothing and folding tasks. The resulting policies achieve 80.3% average task success rate across 10 fabric manipulation tasks on two different physical robotic systems. Results also suggest robustness to fabrics of various colors, sizes, and shapes. See https://tinyurl.com/fabric-descriptors for supplementary material and videos. Aditya Ganapathi, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Daniel Seita, Jennifer Grannen, Minho Hwang, Ryan Hoque, Joseph Gonzalez 0001, Nawid Jamali, Katsu Yamane, Soshi Iba, Kenneth Y. Goldberg	ICRA	4
2021	Disentangling Dense Multi-Cable Knots abstract Disentangling two or more cables often requires many steps to remove crossings between and within cables. We formalize the problem of disentangling multiple cables and present an algorithm, Iterative Reduction Of Non-planar Multiple cAble kNots (IRON-MAN), that outputs robot actions to remove crossings from multi-cable knotted structures. IRON-MAN uses a learned perception system inspired by prior work in single-cable untying to imitate a graph-based supervisor, and operates on RGB image inputs of the workspace. Given a sequence of images as input, the system can disentangle two-cable twists, three-cable braids, and knots of two or three cables, such as overhand, square, carrick bend, sheet bend, crown, and fisherman’s knots. IRON-MAN keeps track of task-relevant keypoints corresponding to cable endpoints and crossings and iteratively disentangles the cables by identifying and undoing crossings that are critical to knot structure. Using a da Vinci surgical robot, we experimentally evaluate the effectiveness of IRON-MAN on disentangling multi-cable knots of types that appear in the training data, as well as generalizing to novel classes of multi-cable knots. Results suggest that IRON-MAN is effective in disentangling knots involving up to three cables with 80.5% success and generalizing to knot types that are not present during training, with cables of identical or distinct colors. Supplementary material and videos can be found at https://tinyurl.com/multi-cable-disentangling. Vainavi Viswanath, Jennifer Grannen, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Ellen R. Novoseller, Jeffrey Ichnowski, Michael Laskey, Joseph Gonzalez 0001, Kenneth Y. Goldberg	IROS	5
2021	ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions Brijen Thananjeyan, Ashwin Balakrishna, Ugo Rosolia, Joseph Gonzalez 0001, Aaron D. Ames, Kenneth Y. Goldberg	WAFR	2
2020	Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data abstract Robotic manipulation of deformable 1D objects such as ropes, cables, and hoses is challenging due to the lack of high-fidelity analytic models and large configuration spaces. Furthermore, learning end-to-end manipulation policies directly from images and physical interaction requires significant time on a robot and can fail to generalize across tasks. We address these challenges using interpretable deep visual representations for rope, extending recent work on dense object descriptors for robot manipulation. This facilitates the design of interpretable and transferable geometric policies built on top of the learned representations, decoupling visual reasoning and control. We present an approach that learns point-pair correspondences between initial and goal rope configurations, which implicitly encodes geometric structure, entirely in simulation from synthetic depth images. We demonstrate that the learned representation — dense depth object descriptors (DDODs) — can be used to manipulate a real rope into a variety of different arrangements either by learning from demonstrations or using interpretable geometric policies. In 50 trials of a knot-tying task with the ABB YuMi Robot, the system achieves a 66% knot-tying success rate from previously unseen configurations. See https://tinyurl.com/rope-learning for supplementary material and videos. Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna, Michael Laskey, Kevin Stone, Joseph Gonzalez 0001, Kenneth Y. Goldberg	ICRA	4
2020	Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor abstract Sequential pulling policies to flatten and smooth fabrics have applications from surgery to manufacturing to home tasks such as bed making and folding clothes. Due to the complexity of fabric states and dynamics, we apply deep imitation learning to learn policies that, given color (RGB), depth (D), or combined color-depth (RGBD) images of a rectangular fabric sample, estimate pick points and pull vectors to spread the fabric to maximize coverage. To generate data, we develop a fabric simulator and an algorithmic supervisor that has access to complete state information. We train policies in simulation using domain randomization and dataset aggregation (DAgger) on three tiers of difficulty in the initial randomized configuration. We present results comparing five baseline policies to learned policies and report systematic comparisons of RGB vs D vs RGBD images as inputs. In simulation, learned policies achieve comparable or superior performance to analytic baselines. In 180 physical experiments with the da Vinci Research Kit (dVRK) surgical robot, RGBD policies trained in simulation attain coverage of 83% to 95% depending on difficulty tier, suggesting that effective fabric smoothing policies can be learned from an algorithmic supervisor and that depth sensing is a valuable addition to color alone. Supplementary material is available at https://sites.google.com/view/fabric-smoothing. Daniel Seita, Aditya Ganapathi, Ryan Hoque, Minho Hwang, Edward Cen, Ajay Kumar Tanwani, Ashwin Balakrishna, Brijen Thananjeyan, Jeffrey Ichnowski, Nawid Jamali, Katsu Yamane, Soshi Iba, John F. Canny, Kenneth Y. Goldberg	IROS	7
2019	Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter abstract When operating in unstructured environments such as warehouses, homes, and retail centers, robots are frequently required to interactively search for and retrieve specific objects from cluttered bins, shelves, or tables. Mechanical Search describes the class of tasks where the goal is to locate and extract a known target object. In this paper, we formalize Mechanical Search and study a version where distractor objects are heaped over the target object in a bin. The robot uses an RGBD perception system and control policies to iteratively select, parameterize, and perform one of 3 actions - push, suction, grasp - until the target object is extracted, or either a time limit is exceeded, or no high confidence push or grasp is available. We present a study of 5 algorithmic policies for mechanical search, with 15,000 simulated trials and 300 physical trials for heaps ranging from 10 to 20 objects. Results suggest that success can be achieved in this long-horizon task with algorithmic policies in over 95% of instances and that the number of actions required scales approximately linearly with the size of the heap. Code and supplementary material can be found at http://ai.stanford.edu/mech-search. Michael Danielczuk, Andrey Kurenkov, Ashwin Balakrishna, Matthew Matl, Roberto Martin Martin, Animesh Garg, Silvio Savarese, Kenneth Y. Goldberg	ICRA	3