Gaurav Sukhatme

Jeremy Morgan, Prajwal Vijay, Hyeonho Oh et al.

Vision-Language-Action (VLA) models demonstrate promising generalization in robotic manipulation, driven by advances in large-scale vision and language pre-training. This progress can be misleading. Despite the zero-shot perception and language capabilities of VLAs, their overall task performance often degrades under distribution shifts, revealing gaps in how these systems translate high-level understanding into robust behavior. To systematically study this gap, we introduce Colosseum V2, a large-scale simulation benchmark for evaluating VLA generalization in robot learning across diverse conditions. The benchmark comprises 28 tasks spanning 13 task categories and two robot morphologies, covering a wide range of manipulation primitives and long-horizon behaviors. Built on the ManiSkill simulator, Colosseum V2 enables fast, GPU-parallelized evaluation and supports both in-domain and out-of-domain testing at scale. We evaluate state-of-the-art methods, including Action Chunking Transformers (ACT) and Pi0.5, and reveal limitations in both base performance and generalization. We demonstrate strong correlations between simulation and real-world metrics that support the ecological validity of the benchmark. By standardizing tasks, metrics, and evaluation protocols within a unified benchmark, Colosseum V2 enables reproducible and fair comparisons, reduced evaluation overhead, and accelerated progress toward general-purpose robot policies.

Hangjie Shi, Leslie Ball, Govind Thattai et al. · amazon-science

The Alexa Prize program has empowered numerous university students to explore, experiment, and showcase their talents in building conversational agents through challenges like the SocialBot Grand Challenge and the TaskBot Challenge. As conversational agents increasingly appear in multimodal and embodied contexts, it is important to explore the affordances of conversational interaction augmented with computer vision and physical embodiment. This paper describes the SimBot Challenge, a new challenge in which university teams compete to build robot assistants that complete tasks in a simulated physical environment. This paper provides an overview of the SimBot Challenge, which included both online and offline challenge phases. We describe the infrastructure and support provided to the teams including Alexa Arena, the simulated environment, and the ML toolkit provided to teams to accelerate their building of vision and language models. We summarize the approaches the participating teams took to overcome research challenges and extract key lessons learned. Finally, we provide analysis of the performance of the competing SimBots during the competition.

Qiaozi Gao, Govind Thattai, Suhaila Shakiah et al.

We introduce Alexa Arena, a user-centric simulation platform for Embodied AI (EAI) research. Alexa Arena provides a variety of multi-room layouts and interactable objects, for the creation of human-robot interaction (HRI) missions. With user-friendly graphics and control mechanisms, Alexa Arena supports the development of gamified robotic tasks readily accessible to general human users, thus opening a new venue for high-efficiency HRI data collection and EAI system evaluation. Along with the platform, we introduce a dialog-enabled instruction-following benchmark and provide baseline results for it. We make Alexa Arena publicly available to facilitate research in building generalizable and assistive embodied agents.

Gautam Salhotra, I-Chun Arthur Liu, Gaurav Sukhatme

Some Learning from Demonstrations (LfD) methods handle small mismatches in the action spaces of the teacher and student. Here we address the case where the teacher's morphology is substantially different from that of the student. Our framework, Morphological Adaptation in Imitation Learning (MAIL), bridges this gap allowing us to train an agent from demonstrations by other agents with significantly different morphologies. MAIL learns from suboptimal demonstrations, so long as they provide $\textit{some}$ guidance towards a desired solution. We demonstrate MAIL on manipulation tasks with rigid and deformable objects including 3D cloth manipulation interacting with rigid obstacles. We train a visual control policy for a robot with one end-effector using demonstrations from a simulated agent with two end-effectors. MAIL shows up to $24\%$ improvement in a normalized performance metric over LfD and non-LfD baselines. It is deployed to a real Franka Panda robot, handles multiple variations in properties for objects (size, rotation, translation), and cloth-specific properties (color, thickness, size, material). An overview is on https://uscresl.github.io/mail .

Nirbhay Modhe, Qiaozi Gao, Ashwin Kalyan et al.

Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions, while model-based methods are able to further exploit unseen states via model rollouts. However, such methods are handicapped in their ability to find unseen states far away from the available offline data due to two factors -- (a) very short rollout horizons in models due to cascading model errors, and (b) model rollouts originating solely from states observed in offline data. We relax the second assumption and present a novel unseen state augmentation strategy to allow exploitation of unseen states where the learned model and value estimates generalize. Our strategy finds unseen states by value-informed perturbations of seen states followed by filtering out states with epistemic uncertainty estimates too high (high error) or too low (too similar to seen data). We observe improved performance in several offline RL tasks and find that our augmentation strategy consistently leads to overall lower average dataset Q-value estimates i.e. more conservative Q-value estimates than a baseline.

Yuqian Jiang, Qiaozi Gao, Govind Thattai et al.

For service robots to become general-purpose in everyday household environments, they need not only a large library of primitive skills, but also the ability to quickly learn novel tasks specified by users. Fine-tuning neural networks on a variety of downstream tasks has been successful in many vision and language domains, but research is still limited on transfer learning between diverse long-horizon tasks. We propose that, compared to reinforcement learning for a new household activity from scratch, home robots can benefit from transferring the value and policy networks trained for similar tasks. We evaluate this idea in the BEHAVIOR simulation benchmark which includes a large number of household activities and a set of action primitives. For easy mapping between state spaces of different tasks, we provide a text-based representation and leverage language models to produce a common embedding space. The results show that the selection of similar source activities can be informed by the semantic similarity of state and goal descriptions with the target task. We further analyze the results and discuss ways to overcome the problem of catastrophic forgetting.

Sumeet Batra, Bryon Tjanaka, Stefanos Nikolaidis et al.

Quality Diversity (QD) has shown great success in discovering high-performing, diverse policies for robot skill learning. While current benchmarks have led to the development of powerful QD methods, we argue that new paradigms must be developed to facilitate open-ended search and generalizability. In particular, many methods focus on learning diverse agents that each move to a different xy position in MAP-Elites-style bounded archives. Here, we show that such tasks can be accomplished with a single, goal-conditioned policy paired with a classical planner, achieving O(1) space complexity w.r.t. the number of policies and generalization to task variants. We hypothesize that this approach is successful because it extracts task-invariant structural knowledge by modeling a relational graph between adjacent cells in the archive. We motivate this view with emerging evidence from computational neuroscience and explore connections between QD and models of cognitive maps in human and other animal brains. We conclude with a discussion exploring the relationships between QD and cognitive maps, and propose future research directions inspired by cognitive maps towards future generalizable algorithms capable of truly open-ended search.

I-Chun Arthur Liu, Sicheng He, Daniel Seita et al.

Bimanual manipulation is critical to many robotics applications. In contrast to single-arm manipulation, bimanual manipulation tasks are challenging due to higher-dimensional action spaces. Prior works leverage large amounts of data and primitive actions to address this problem, but may suffer from sample inefficiency and limited generalization across various tasks. To this end, we propose VoxAct-B, a language-conditioned, voxel-based method that leverages Vision Language Models (VLMs) to prioritize key regions within the scene and reconstruct a voxel grid. We provide this voxel grid to our bimanual manipulation policy to learn acting and stabilizing actions. This approach enables more efficient policy learning from voxels and is generalizable to different tasks. In simulation, we show that VoxAct-B outperforms strong baselines on fine-grained bimanual manipulation tasks. Furthermore, we demonstrate VoxAct-B on real-world $\texttt{Open Drawer}$ and $\texttt{Open Jar}$ tasks using two UR5s. Code, data, and videos are available at https://voxact-b.github.io.

Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme et al.

Bimanual robot learning from demonstrations is fundamentally limited by the cost and narrow visual diversity of real-world data, which constrains policy robustness across viewpoints, object configurations, and embodiments. We present Canny-guided Robot Data Generation using Video Diffusion Transformers (CRAFT), a video diffusion-based framework for scalable bimanual demonstration generation that synthesizes temporally coherent manipulation videos while producing action labels. By conditioning video diffusion on edge-based structural cues extracted from simulator-generated trajectories, CRAFT produces physically plausible trajectory variations and supports a unified augmentation pipeline spanning object pose changes, camera viewpoints, lighting and background variations, cross-embodiment transfer, and multi-view synthesis. We leverage a pre-trained video diffusion model to convert simulated videos, along with action labels from the simulation trajectories, into action-consistent demonstrations. Starting from only a few real-world demonstrations, CRAFT generates a large, visually diverse set of photorealistic training data, bypassing the need to replay demonstrations on the real robot (Sim2Real). Across simulated and real-world bimanual tasks, CRAFT improves success rates over existing augmentation strategies and straightforward data scaling, demonstrating that diffusion-based video generation can substantially expand demonstration diversity and improve generalization for dual-arm manipulation tasks. Our project website is available at: https://craftaug.github.io/

Aleksei Petrenko, Zhehui Huang, Tushar Kumar et al.

Increasing the scale of reinforcement learning experiments has allowed researchers to achieve unprecedented results in both training sophisticated agents for video games, and in sim-to-real transfer for robotics. Typically such experiments rely on large distributed systems and require expensive hardware setups, limiting wider access to this exciting area of research. In this work we aim to solve this problem by optimizing the efficiency and resource utilization of reinforcement learning algorithms instead of relying on distributed computation. We present the "Sample Factory", a high-throughput training system optimized for a single-machine setting. Our architecture combines a highly efficient, asynchronous, GPU-based sampler with off-policy correction techniques, allowing us to achieve throughput higher than $10^5$ environment frames/second on non-trivial control problems in 3D without sacrificing sample efficiency. We extend Sample Factory to support self-play and population-based training and apply these techniques to train highly capable agents for a multiplayer first-person shooter game. The source code is available at https://github.com/alex-petrenko/sample-factory

Sarah Bechtle, Artem Molchanov, Yevgen Chebotar et al.

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process, with the view of producing models which train faster and more robustly. Concretely, we present a meta-learning method for learning parametric loss functions that can generalize across different tasks and model architectures. We develop a pipeline for meta-training such loss functions, targeted at maximizing the performance of the model trained under them. The loss landscape produced by our learned losses significantly improves upon the original task-specific losses in both supervised and reinforcement learning tasks. Furthermore, we show that our meta-learning framework is flexible enough to incorporate additional information at meta-train time. This information shapes the learned loss function such that the environment does not need to provide this information during meta-test time. We make our code available at https://sites.google.com/view/mlthree.

Jialu Li, Aishwarya Padmakumar, Gaurav Sukhatme et al. · amazon-science

Outdoor Vision-and-Language Navigation (VLN) requires an agent to navigate through realistic 3D outdoor environments based on natural language instructions. The performance of existing VLN methods is limited by insufficient diversity in navigation environments and limited training data. To address these issues, we propose VLN-Video, which utilizes the diverse outdoor environments present in driving videos in multiple cities in the U.S. augmented with automatically generated navigation instructions and actions to improve outdoor VLN performance. VLN-Video combines the best of intuitive classical approaches and modern deep learning techniques, using template infilling to generate grounded navigation instructions, combined with an image rotation similarity-based navigation action predictor to obtain VLN style data from driving videos for pretraining deep learning VLN models. We pre-train the model on the Touchdown dataset and our video-augmented dataset created from driving videos with three proxy tasks: Masked Language Modeling, Instruction and Trajectory Matching, and Next Action Prediction, so as to learn temporally-aware and visually-aligned instruction representations. The learned instruction representation is adapted to the state-of-the-art navigator when fine-tuning on the Touchdown dataset. Empirical results demonstrate that VLN-Video significantly outperforms previous state-of-the-art models by 2.1% in task completion rate, achieving a new state-of-the-art on the Touchdown dataset.

I-Chun Arthur Liu, Jason Chen, Gaurav Sukhatme et al.

Learning bimanual manipulation is challenging due to its high dimensionality and tight coordination required between two arms. Eye-in-hand imitation learning, which uses wrist-mounted cameras, simplifies perception by focusing on task-relevant views. However, collecting diverse demonstrations remains costly, motivating the need for scalable data augmentation. While prior work has explored visual augmentation in single-arm settings, extending these approaches to bimanual manipulation requires generating viewpoint-consistent observations across both arms and producing corresponding action labels that are both valid and feasible. In this work, we propose Diffusion for COordinated Dual-arm Data Augmentation (D-CODA), a method for offline data augmentation tailored to eye-in-hand bimanual imitation learning that trains a diffusion model to synthesize novel, viewpoint-consistent wrist-camera images for both arms while simultaneously generating joint-space action labels. It employs constrained optimization to ensure that augmented states involving gripper-to-object contacts adhere to constraints suitable for bimanual coordination. We evaluate D-CODA on 5 simulated and 3 real-world tasks. Our results across 2250 simulation trials and 300 real-world trials demonstrate that it outperforms baselines and ablations, showing its potential for scalable data augmentation in eye-in-hand bimanual manipulation. Our project website is at: https://dcodaaug.github.io/D-CODA/.

Shipeng Liu, FNU Shrutika, Boshen Zhang et al.

Effective human-robot collaboration requires robot to adopt their roles and levels of support based on human needs, task requirements, and complexity. Traditional human-robot teaming often relies on a pre-determined robot communication scheme, restricting teamwork adaptability in complex tasks. Leveraging strong communication capabilities of Large Language Models (LLMs), we propose a Human-Robot Teaming Framework with Multi-Modal Language feedback (HRT-ML), a framework designed to enhance human-robot interaction by adjusting the frequency and content of language-based feedback. HRT-ML framework includes two core modules: a Coordinator for high-level, low-frequency strategic guidance, and a Manager for subtask-specific, high-frequency instructions, enabling passive and active interactions with human teammates. To assess the impact of language feedback in collaborative scenarios, we conducted experiments in an enhanced Overcooked environment with varying levels of task complexity (easy, medium, hard) and feedback frequency (inactive, passive, active, superactive). Our results show that as task complexity increases relative to human capabilities, human teammates exhibited a stronger preference towards robotic agents that can offer frequent, proactive support. However, when task complexities exceed the LLM's capacity, noisy and inaccurate feedback from superactive robotic agents can instead hinder team performance, as it requires human teammates to increase their effort to interpret and respond to a large number of communications, with limited performance return. Our results offer a general principle for robotic agents to dynamically adjust their levels and frequencies of communications to work seamlessly with humans and achieve improved teaming performance.

Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme et al.

Training robust bimanual manipulation policies via imitation learning requires demonstration data with broad coverage over robot poses, contacts, and scene contexts. However, collecting diverse and precise real-world demonstrations is costly and time-consuming, which hinders scalability. Prior works have addressed this with data augmentation, typically for either eye-in-hand (wrist camera) setups with RGB inputs or for generating novel images without paired actions, leaving augmentation for eye-to-hand (third-person) RGB-D training with new action labels less explored. In this paper, we propose Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation (ROPA), an offline imitation learning data augmentation method that fine-tunes Stable Diffusion to synthesize third-person RGB and RGB-D observations of novel robot poses. Our approach simultaneously generates corresponding joint-space action labels while employing constrained optimization to enforce physical consistency through appropriate gripper-to-object contact constraints in bimanual scenarios. We evaluate our method on 5 simulated and 3 real-world tasks. Our results across 2625 simulation trials and 300 real-world trials demonstrate that ROPA outperforms baselines and ablations, showing its potential for scalable RGB and RGB-D data augmentation in eye-to-hand bimanual manipulation. Our project website is available at: https://ropaaug.github.io/.

Sumeet Batra, Bryon Tjanaka, Matthew C. Fontaine et al.

Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement Learning (QD-RL) is an emerging research area that blends the best aspects of both fields -- Quality Diversity (QD) provides a principled form of exploration and produces collections of behaviorally diverse agents, while Reinforcement Learning (RL) provides a powerful performance improvement operator enabling generalization across tasks and dynamic environments. Existing QD-RL approaches have been constrained to sample efficient, deterministic off-policy RL algorithms and/or evolution strategies, and struggle with highly stochastic environments. In this work, we, for the first time, adapt on-policy RL, specifically Proximal Policy Optimization (PPO), to the Differentiable Quality Diversity (DQD) framework and propose additional improvements over prior work that enable efficient optimization and discovery of novel skills on challenging locomotion tasks. Our new algorithm, Proximal Policy Gradient Arborescence (PPGA), achieves state-of-the-art results, including a 4x improvement in best reward over baselines on the challenging humanoid domain.

Zhiwei Jia, Kaixiang Lin, Yizhou Zhao et al.

Recent years have witnessed an emerging paradigm shift toward embodied artificial intelligence, in which an agent must learn to solve challenging tasks by interacting with its environment. There are several challenges in solving embodied multimodal tasks, including long-horizon planning, vision-and-language grounding, and efficient exploration. We focus on a critical bottleneck, namely the performance of planning and navigation. To tackle this challenge, we propose a Neural SLAM approach that, for the first time, utilizes several modalities for exploration, predicts an affordance-aware semantic map, and plans over it at the same time. This significantly improves exploration efficiency, leads to robust long-horizon planning, and enables effective vision-and-language grounding. With the proposed Affordance-aware Multimodal Neural SLAM (AMSLAM) approach, we obtain more than 40% improvement over prior published work on the ALFRED benchmark and set a new state-of-the-art generalization performance at a success rate of 23.48% on the test unseen scenes.

Nicholas Roy, Ingmar Posner, Tim Barfoot et al.

Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains. Consequently, the notion of applying learning methods to a particular problem set has become an established and valuable modus operandi to advance a particular field. In this article we argue that such an approach does not straightforwardly extended to robotics -- or to embodied intelligence more generally: systems which engage in a purposeful exchange of energy and information with a physical environment. In particular, the purview of embodied intelligent agents extends significantly beyond the typical considerations of main-stream machine learning approaches, which typically (i) do not consider operation under conditions significantly different from those encountered during training; (ii) do not consider the often substantial, long-lasting and potentially safety-critical nature of interactions during learning and deployment; (iii) do not require ready adaptation to novel tasks while at the same time (iv) effectively and efficiently curating and extending their models of the world through targeted and deliberate actions. In reality, therefore, these limitations result in learning-based systems which suffer from many of the same operational shortcomings as more traditional, engineering-based approaches when deployed on a robot outside a well defined, and often narrow operating envelope. Contrary to viewing embodied intelligence as another application domain for machine learning, here we argue that it is in fact a key driver for the advancement of machine learning technology. In this article our goal is to highlight challenges and opportunities that are specific to embodied intelligence and to propose research directions which may significantly advance the state-of-the-art in robot learning.

Alessandro Suglia, Qiaozi Gao, Jesse Thomason et al.

Language-guided robots performing home and office tasks must navigate in and interact with the world. Grounding language instructions against visual observations and actions to take in an environment is an open challenge. We present Embodied BERT (EmBERT), a transformer-based model which can attend to high-dimensional, multi-modal inputs across long temporal horizons for language-conditioned task completion. Additionally, we bridge the gap between successful object-centric navigation models used for non-interactive agents and the language-guided visual task completion benchmark, ALFRED, by introducing object navigation targets for EmBERT training. We achieve competitive performance on the ALFRED benchmark, and EmBERT marks the first transformer-based model to successfully handle the long-horizon, dense, multi-modal histories of ALFRED, and the first ALFRED model to utilize object-centric navigation targets.

K. R. Zentner, Ryan Julian, Ujjwal Puri et al.

We explore possible methods for multi-task transfer learning which seek to exploit the shared physical structure of robotics tasks. Specifically, we train policies for a base set of pre-training tasks, then experiment with adapting to new off-distribution tasks, using simple architectural approaches for re-using these policies as black-box priors. These approaches include learning an alignment of either the observation space or action space from a base to a target task to exploit rigid body structure, and methods for learning a time-domain switching policy across base tasks which solves the target task, to exploit temporal coherence. We find that combining low-complexity target policy classes, base policies as black-box priors, and simple optimization algorithms allows us to acquire new tasks outside the base task distribution, using small amounts of offline training data.

Shoubhik Debnath, Gaurav Sukhatme, Lantao Liu

We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where firstly, we approximate a model from Model-Free reinforcement learning. Then, we leverage this approximate model along with a notion of reachability using Mean First Passage Times to perform Model-Based reinforcement learning. Built on such a novel observation, we design two new algorithms - Mean First Passage Time based Q-Learning (MFPT-Q) and Mean First Passage Time based DYNA (MFPT-DYNA), that have been fundamentally modified from the state-of-the-art reinforcement learning techniques. Preliminary results have shown that our hybrid approaches converge with much fewer iterations than their corresponding state-of-the-art counterparts and therefore requiring much fewer samples and much fewer training trials to converge.

Shoubhik Debnath, Lantao Liu, Gaurav Sukhatme

A new mechanism for efficiently solving the Markov decision processes (MDPs) is proposed in this paper. We introduce the notion of reachability landscape where we use the Mean First Passage Time (MFPT) as a means to characterize the reachability of every state in the state space. We show that such reachability characterization very well assesses the importance of states and thus provides a natural basis for effectively prioritizing states and approximating policies. Built on such a novel observation, we design two new algorithms -- Mean First Passage Time based Value Iteration (MFPT-VI) and Mean First Passage Time based Policy Iteration (MFPT-PI) -- that have been modified from the state-of-the-art solution methods. To validate our design, we have performed numerical evaluations in robotic decision-making scenarios, by comparing the proposed new methods with corresponding classic baseline mechanisms. The evaluation results showed that MFPT-VI and MFPT-PI have outperformed the state-of-the-art solutions in terms of both practical runtime and number of iterations. Aside from the advantage of fast convergence, this new solution method is intuitively easy to understand and practically simple to implement.

Shoubhik Debnath, Lantao Liu, Gaurav Sukhatme

The solution convergence of Markov Decision Processes (MDPs) can be accelerated by prioritized sweeping of states ranked by their potential impacts to other states. In this paper, we present new heuristics to speed up the solution convergence of MDPs. First, we quantify the level of reachability of every state using the Mean First Passage Time (MFPT) and show that such reachability characterization very well assesses the importance of states which is used for effective state prioritization. Then, we introduce the notion of backup differentials as an extension to the prioritized sweeping mechanism, in order to evaluate the impacts of states at an even finer scale. Finally, we extend the state prioritization to the temporal process, where only partial sweeping can be performed during certain intermediate value iteration stages. To validate our design, we have performed numerical evaluations by comparing the proposed new heuristics with corresponding classic baseline mechanisms. The evaluation results showed that our reachability based framework and its differential variants have outperformed the state-of-the-art solutions in terms of both practical runtime and number of iterations.

Zhanpeng He, Ryan Julian, Eric Heiden et al.

Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful sim-to-real transfer systems have difficulty producing policies which generalize across tasks, despite training for thousands of hours equivalent real robot time. To address this shortcoming, we present a novel approach to efficiently learning new robotic skills directly on a real robot, based on model-predictive control (MPC) and an algorithm for learning task representations. In short, we show how to reuse the simulation from the pre-training step of sim-to-real methods as a tool for foresight, allowing the sim-to-real policy adapt to unseen tasks. Rather than end-to-end learning policies for single tasks and attempting to transfer them, we first use simulation to simultaneously learn (1) a continuous parameterization (i.e. a skill embedding or latent) of task-appropriate primitive skills, and (2) a single policy for these skills which is conditioned on this representation. We then directly transfer our multi-skill policy to a real robot, and actuate the robot by choosing sequences of skill latents which actuate the policy, with each latent corresponding to a pre-learned primitive skill controller. We complete unseen tasks by choosing new sequences of skill latents to control the robot using MPC, where our MPC model is composed of the pre-trained skill policy executed in the simulation environment, run in parallel with the real robot. We discuss the background and principles of our method, detail its practical implementation, and evaluate its performance by using our method to train a real Sawyer Robot to achieve motion tasks such as drawing and block pushing.

Ryan Julian, Eric Heiden, Zhanpeng He et al.

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that are parameterized in a way that makes them easily reusable. This diversity and parameterization of low-level skills allows us to find a transferable policy that is able to use combinations and variations of different skills to solve more complex, high-level tasks. In particular, we first use simulation to jointly learn a policy for a set of low-level skills, and a "skill embedding" parameterization which can be used to compose them. Later, we learn high-level policies which actuate the low-level policies via this skill embedding parameterization. The high-level policies encode how and when to reuse the low-level skills together to achieve specific high-level tasks. Importantly, our method learns to control a real robot in joint-space to achieve these high-level tasks with little or no on-robot time, despite the fact that the low-level policies may not be perfectly transferable from simulation to real, and that the low-level skills were not trained on any examples of high-level tasks. We illustrate the principles of our method using informative simulation experiments. We then verify its usefulness for real robotics problems by learning, transferring, and composing free-space and contact motion skills on a Sawyer robot using only joint-space control. We experiment with several techniques for composing pre-learned skills, and find that our method allows us to use both learning-based approaches and efficient search-based planning to achieve high-level tasks using only pre-learned skills.

Artem Molchanov, Karol Hausman, Stan Birchfield et al.

Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying reinforcement learning in these scenarios can be challenging. Common approaches for tackling this problem include reward engineering with auxiliary rewards, requiring domain-specific knowledge or changing the objective. In this work, we introduce a method based on region-growing that allows learning in an environment with any pair of initial and goal states. Our algorithm first learns how to move between nearby states and then increases the difficulty of the start-goal transitions as the agent's performance improves. This approach creates an efficient curriculum for learning the objective behavior of reaching any goal from any initial state. In addition, we describe a method to adaptively adjust expansion of the growing region that allows automatic adjustment of the key exploration hyperparameter to environments with different requirements. We evaluate our approach on a set of simulated navigation and manipulation tasks, where we demonstrate that our algorithm can efficiently learn a policy in the presence of sparse rewards.

Karol Hausman, Yevgen Chebotar, Stefan Schaal et al.

Imitation learning has traditionally been applied to learn a single task from demonstrations thereof. The requirement of structured and isolated demonstrations limits the scalability of imitation learning approaches as they are difficult to apply to real-world scenarios, where robots have to be able to execute a multitude of tasks. In this paper, we propose a multi-modal imitation learning framework that is able to segment and imitate skills from unlabelled and unstructured demonstrations by learning skill segmentation and imitation learning jointly. The extensive simulation results indicate that our method can efficiently separate the demonstrations into individual skills and learn to imitate them using a single multi-modal policy. The video of our experiments is available at http://sites.google.com/view/nips17intentiongan

Yevgen Chebotar, Karol Hausman, Marvin Zhang et al.

Reinforcement learning (RL) algorithms for real-world robotic applications need a data-efficient learning process and the ability to handle complex, unknown dynamical systems. These requirements are handled well by model-based and model-free RL approaches, respectively. In this work, we aim to combine the advantages of these two types of methods in a principled manner. By focusing on time-varying linear-Gaussian policies, we enable a model-based algorithm based on the linear quadratic regulator (LQR) that can be integrated into the model-free framework of path integral policy improvement (PI2). We can further combine our method with guided policy search (GPS) to train arbitrary parameterized policies such as deep neural networks. Our simulation and real-world experiments demonstrate that this method can solve challenging manipulation tasks with comparable or better performance than model-free methods while maintaining the sample efficiency of model-based methods. A video presenting our results is available at https://sites.google.com/site/icml17pilqr

Karol Hausman, James Preiss, Gaurav Sukhatme et al.

We study the nonlinear observability of a systems states in view of how well they are observable and what control inputs would improve the convergence of their estimates. We use these insights to develop an observability-aware trajectory-optimization framework for nonlinear systems that produces trajectories well suited for self-calibration. Common trajectory-planning algorithms tend to generate motions that lead to an unobservable subspace of the system state, causing suboptimal state estimation. We address this problem with a method that reasons about the quality of observability while respecting system dynamics and motion constraints to yield the optimal trajectory for rapid convergence of the self-calibration states (or other user-chosen states). Experiments performed on a simulated quadrotor system with a GPS-IMU sensor suite demonstrate the benefits of the optimized observability-aware trajectories when compared to a covariance-based approach and multiple heuristic approaches. Our method is approx. 80x faster than the covariance-based approach and achieves better results than any other approach in the self-calibration task. We applied our method to a waypoint navigation task and achieved a approx. 2x improvement in the integrated RMSE of the global position estimates and approx. 4x improvement in the integrated RMSE of the GPS-IMU transformation estimates compared to a minimal-energy trajectory planner.

Jeannette Bohg, Karol Hausman, Bharath Sankaran et al.

Recent approaches in robotics follow the insight that perception is facilitated by interaction with the environment. These approaches are subsumed under the term of Interactive Perception (IP). It provides the following benefits: (i) interaction with the environment creates a rich sensory signal that would otherwise not be present and (ii) knowledge of the regularity in the combined space of sensory data and action parameters facilitate the prediction and interpretation of the signal. In this survey we postulate this as a principle and collect evidence in support by analyzing and categorizing existing work in this area. We also provide an overview of the most important applications of Interactive Perception. We close this survey by discussing remaining open questions. Thereby, we hope to define a field and inspire future work.

Jie Chen, Kian Hsiang Low, Colin Keng-Yan Tan et al.

The problem of modeling and predicting spatiotemporal traffic phenomena over an urban road network is important to many traffic applications such as detecting and forecasting congestion hotspots. This paper presents a decentralized data fusion and active sensing (D2FAS) algorithm for mobile sensors to actively explore the road network to gather and assimilate the most informative data for predicting the traffic phenomenon. We analyze the time and communication complexity of D2FAS and demonstrate that it can scale well with a large number of observations and sensors. We provide a theoretical guarantee on its predictive performance to be equivalent to that of a sophisticated centralized sparse approximation for the Gaussian process (GP) model: The computation of such a sparse approximate GP model can thus be parallelized and distributed among the mobile sensors (in a Google-like MapReduce paradigm), thereby achieving efficient and scalable prediction. We also theoretically guarantee its active sensing performance that improves under various practical environmental conditions. Empirical evaluation on real-world urban road network data shows that our D2FAS algorithm is significantly more time-efficient and scalable than state-oftheart centralized algorithms while achieving comparable predictive performance.