Causal Policy Gradient for Whole-Body Mobile Manipulation

• URL: http://arxiv.org/abs/2305.04866v4
• Date: Thu, 28 Sep 2023 16:17:08 GMT
• Title: Causal Policy Gradient for Whole-Body Mobile Manipulation
• Authors: Jiaheng Hu, Peter Stone, Roberto Mart\'in-Mart\'in
• Abstract summary: We introduce Causal MoMa, a new reinforcement learning framework to train policies for typical MoMa tasks. We evaluate the performance of Causal MoMa on three types of simulated robots across different MoMa tasks.
• Score: 39.3461626518495
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Developing the next generation of household robot helpers requires combining locomotion and interaction capabilities, which is generally referred to as mobile manipulation (MoMa). MoMa tasks are difficult due to the large action space of the robot and the common multi-objective nature of the task, e.g., efficiently reaching a goal while avoiding obstacles. Current approaches often segregate tasks into navigation without manipulation and stationary manipulation without locomotion by manually matching parts of the action space to MoMa sub-objectives (e.g. learning base actions for locomotion objectives and learning arm actions for manipulation). This solution prevents simultaneous combinations of locomotion and interaction degrees of freedom and requires human domain knowledge for both partitioning the action space and matching the action parts to the sub-objectives. In this paper, we introduce Causal MoMa, a new reinforcement learning framework to train policies for typical MoMa tasks that makes use of the most favorable subspace of the robot's action space to address each sub-objective. Causal MoMa automatically discovers the causal dependencies between actions and terms of the reward function and exploits these dependencies through causal policy gradient that reduces gradient variance compared to previous state-of-the-art reinforcement learning algorithms, improving convergence and results. We evaluate the performance of Causal MoMa on three types of simulated robots across different MoMa tasks and demonstrate success in transferring the policies trained in simulation directly to a real robot, where our agent is able to follow moving goals and react to dynamic obstacles while simultaneously and synergistically controlling the whole-body: base, arm, and head. More information at https://sites.google.com/view/causal-moma.

Related papers

• Zero-Cost Whole-Body Teleoperation for Mobile Manipulation [8.71539730969424]
  MoMa-Teleop is a novel teleoperation method that delegates the base motions to a reinforcement learning agent. We demonstrate that our approach results in a significant reduction in task completion time across a variety of robots and tasks.
  arXiv  Detail & Related papers  (2024-09-23T15:09:45Z)
• HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation [7.01404330241523]
  HYPERmotion is a framework that learns, selects and plans behaviors based on tasks in different scenarios. We combine reinforcement learning with whole-body optimization to generate motion for 38 actuated joints. Experiments in simulation and real-world show that learned motions can efficiently adapt to new tasks.
  arXiv  Detail & Related papers  (2024-06-20T18:21:24Z)
• Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration [8.343657309038285]
  Reinforcement Learning is a powerful framework for developing such robot controllers. We propose a multimodal exploration approach through categorical distributions, which enables us to train planar pushing RL policies. We show that the learned policies are robust to external disturbances and observation noise, and scale to tasks with multiple pushers.
  arXiv  Detail & Related papers  (2023-08-04T16:55:00Z)
• Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration [68.94506047556412]
  We propose to leverage a sequential bias to learn control policies for complex robotic tasks using a single demonstration. We show that DCIL-II can solve with unprecedented sample efficiency some challenging simulated tasks such as humanoid locomotion and stand-up.
  arXiv  Detail & Related papers  (2022-11-09T10:28:40Z)
• Model Predictive Control for Fluid Human-to-Robot Handovers [50.72520769938633]
  Planning motions that take human comfort into account is not a part of the human-robot handover process. We propose to generate smooth motions via an efficient model-predictive control framework. We conduct human-to-robot handover experiments on a diverse set of objects with several users.
  arXiv  Detail & Related papers  (2022-03-31T23:08:20Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)
• Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation [16.79185733369416]
  We propose a two-stage architecture for autonomous interaction with large articulated objects in unknown environments. The first stage uses a learned model to estimate the articulated model of a target object from an RGB-D input and predicts an action-conditional sequence of states for interaction. The second stage comprises of a whole-body motion controller to manipulate the object along the generated kinematic plan.
  arXiv  Detail & Related papers  (2021-03-18T21:32:18Z)
• Neural Dynamic Policies for End-to-End Sensorimotor Learning [51.24542903398335]
  The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces. We propose Neural Dynamic Policies (NDPs) that make predictions in trajectory distribution space. NDPs outperform the prior state-of-the-art in terms of either efficiency or performance across several robotic control tasks.
  arXiv  Detail & Related papers  (2020-12-04T18:59:32Z)
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation [99.2543521972137]
  ReLMoGen is a framework that combines a learned policy to predict subgoals and a motion generator to plan and execute the motion needed to reach these subgoals. Our method is benchmarked on a diverse set of seven robotics tasks in photo-realistic simulation environments. ReLMoGen shows outstanding transferability between different motion generators at test time, indicating a great potential to transfer to real robots.
  arXiv  Detail & Related papers  (2020-08-18T08:05:15Z)

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.