Continuously Improving Mobile Manipulation with Autonomous Real-World RL

• URL: http://arxiv.org/abs/2409.20568v1
• Date: Mon, 30 Sep 2024 17:59:50 GMT
• Title: Continuously Improving Mobile Manipulation with Autonomous Real-World RL
• Authors: Russell Mendonca, Emmanuel Panov, Bernadette Bucher, Jiuguang Wang, Deepak Pathak,
• Abstract summary: We present a fully autonomous real-world RL framework for mobile manipulation that can learn policies without extensive instrumentation or human supervision. This is enabled by task-relevant autonomy, which guides exploration towards object interactions and prevents stagnation near goal states. We demonstrate that our approach allows Spot robots to continually improve their performance on a set of four challenging mobile manipulation tasks.
• Score: 33.085671103158866
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a fully autonomous real-world RL framework for mobile manipulation that can learn policies without extensive instrumentation or human supervision. This is enabled by 1) task-relevant autonomy, which guides exploration towards object interactions and prevents stagnation near goal states, 2) efficient policy learning by leveraging basic task knowledge in behavior priors, and 3) formulating generic rewards that combine human-interpretable semantic information with low-level, fine-grained observations. We demonstrate that our approach allows Spot robots to continually improve their performance on a set of four challenging mobile manipulation tasks, obtaining an average success rate of 80% across tasks, a 3-4 improvement over existing approaches. Videos can be found at https://continual-mobile-manip.github.io/

Related papers

• Self-Supervised Learning of Grasping Arbitrary Objects On-the-Move [8.445514342786579]
  This study introduces three fully convolutional neural network (FCN) models to predict static grasp primitive, dynamic grasp primitive, and residual moving velocity error from visual inputs. The proposed method achieved the highest grasping accuracy and pick-and-place efficiency.
  arXiv  Detail & Related papers  (2024-11-15T02:59:16Z)
• Learning the Generalizable Manipulation Skills on Soft-body Tasks via Guided Self-attention Behavior Cloning Policy [9.345203561496552]
  GP2E behavior cloning policy can guide the agent to learn the generalizable manipulation skills from soft-body tasks. Our findings highlight the potential of our method to improve the generalization abilities of Embodied AI models.
  arXiv  Detail & Related papers  (2024-10-08T07:31:10Z)
• Hand-Object Interaction Pretraining from Videos [77.92637809322231]
  We learn general robot manipulation priors from 3D hand-object interaction trajectories. We do so by sharing both the human hand and the manipulated object in 3D space and human motions to robot actions. We empirically demonstrate that finetuning this policy, with both reinforcement learning (RL) and behavior cloning (BC), enables sample-efficient adaptation to downstream tasks and simultaneously improves robustness and generalizability compared to prior approaches.
  arXiv  Detail & Related papers  (2024-09-12T17:59:07Z)
• EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning [36.0274770291531]
  We propose Equibot, a robust, data-efficient, and generalizable approach for robot manipulation task learning. Our approach combines SIM(3)-equivariant neural network architectures with diffusion models. We show that our method can easily generalize to novel objects and scenes after learning from just 5 minutes of human demonstrations in each task.
  arXiv  Detail & Related papers  (2024-07-01T17:09:43Z)
• Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning [58.3994826169858]
  We introduce RoboFuME, a reset-free fine-tuning system for robotic reinforcement learning. Our insights are to utilize offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy. Our method can incorporate data from an existing robot dataset and improve on a target task within as little as 3 hours of autonomous real-world experience.
  arXiv  Detail & Related papers  (2023-10-23T17:50:08Z)
• Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning [54.636562516974884]
  In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. In this work, we propose MEDAL++, a novel design for self-improving robotic systems. The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
  arXiv  Detail & Related papers  (2023-03-02T18:51:38Z)
• Multi-skill Mobile Manipulation for Object Rearrangement [75.62774690484022]
  We study a modular approach to tackle long-horizon mobile manipulation tasks for object rearrangement. Prior work chains multiple stationary manipulation skills with a point-goal navigation skill, which are learned individually on subtasks. We operationalize these ideas by implementing mobile manipulation skills rather than stationary ones and training a navigation skill trained with region goal instead of point goal.
  arXiv  Detail & Related papers  (2022-09-06T19:02:08Z)
• Robot Learning of Mobile Manipulation with Reachability Behavior Priors [38.49783454634775]
  Mobile Manipulation (MM) systems are ideal candidates for taking up the role of a personal assistant in unstructured real-world environments. Among other challenges, MM requires effective coordination of the robot's embodiments for executing tasks that require both mobility and manipulation. We study the integration of robotic reachability priors in actor-critic RL methods for accelerating the learning of MM for reaching and fetching tasks.
  arXiv  Detail & Related papers  (2022-03-08T12:44:42Z)
• ReLMM: Practical RL for Learning Mobile Manipulation Skills Using Only Onboard Sensors [64.2809875343854]
  We study how robots can autonomously learn skills that require a combination of navigation and grasping. Our system, ReLMM, can learn continuously on a real-world platform without any environment instrumentation. After a grasp curriculum training phase, ReLMM can learn navigation and grasping together fully automatically, in around 40 hours of real-world training.
  arXiv  Detail & Related papers  (2021-07-28T17:59:41Z)
• A Framework for Efficient Robotic Manipulation [79.10407063260473]
  We show that a single robotic arm can learn sparse-reward manipulation policies from pixels. We show that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels.
  arXiv  Detail & Related papers  (2020-12-14T22:18:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.