Corpus ID: 226254352

Learning a Decentralized Multi-arm Motion Planner

  title={Learning a Decentralized Multi-arm Motion Planner},
  author={Huy Ha and Jingxi Xu and Shuran Song},
We present a closed-loop multi-arm motion planner that is scalable and flexible with team size. Traditional multi-arm robot systems have relied on centralized motion planners, whose runtimes often scale exponentially with team size, and thus, fail to handle dynamic environments with open-loop control. In this paper, we tackle this problem with multi-agent reinforcement learning, where a decentralized policy is trained to control one robot arm in the multi-arm system to reach its target end… Expand

Figures and Tables from this paper

CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL
A residual-RL method is presented that leverages a greedy goalreaching RL policy as the base to improve exploration, and the base policy is augmented with residual state-action values and residual actions learned from images to avoid obstacles. Expand
Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation
This work distill a state-based motion planner augmented policy to a visual control policy via (1) visual behavioral cloning to remove the motion planner dependency along with its jittery motion, and (2) vision-based reinforcement learning with the guidance of the smoothed trajectories from the behavioral cloning agent. Expand
Decentralized Multi-Agent Control of a Manipulator in Continuous Task Learning
Many real-world tasks require multiple agents to work together. When talking about multiple agents in robotics, it is usually referenced to multiple manipulators in collaboration to solve a givenExpand
Motion Planning for Dual-Arm Robot Based on Soft Actor-Critic
In this paper, a motion planning method based on the Soft Actor-Critic (SAC) is designed for a dual-arm robot with two 7-Degree-of-Freedom (7-DOF) arms so that the robot can effectively avoidExpand
Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly
A scalable planning system which enables parallelization of complex task and motion planning problems by iteratively solving smaller sub-problems by combining optimization methods to solve for manipulation constraints with a sampling-based bi-directional space-time path planner. Expand
V-MAO: Generative Modeling for Multi-Arm Manipulation of Articulated Objects
V-MAO is presented, a framework for learning multi-arm manipulation of articulated objects that includes a variational generative model that learns contact point distribution over object rigid parts for each robot arm. Expand
Robust Multi-Robot Trajectory Generation Using Alternating Direction Method of Multiplier
This work proposes a variant of alternating direction method of multiplier (ADMM) to solve constrained trajectory optimization problems, and inherits the theoretical properties of primal interior point method (P-IPM), i.e., guaranteed collision avoidance and homotopy preservation, while being orders of magnitude faster. Expand
Provably Robust & Efficient Multi-Robot Trajectory Generation Using Alternating Direction Method of Multiplier
We propose a variant of alternating direction method of multiplier (ADMM) to solve constrained trajectory optimization problems. Our ADMM framework breaks a joint optimization into smallExpand
Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimation
An unsupervised vision-based system to estimate the joint configurations of the robot arm from a sequence of RGB or RGB-D images without knowing the model a priori, and then adapt it to the task of category-independent articulated object pose estimation, which achieves higher accuracy than the state-of-the-art supervised methods. Expand
DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation
Experimental results show that the proposed intrinsic regularization successfully avoids domination and reduces conflicts for the policies, which leads to significantly more efficient and safer cooperative strategies than all the baselines. Expand


A unified framework for coordinated multi-arm motion planning
This work introduces a centralized inverse kinematics solver under self-collision avoidance constraints, formulated as a quadratic program and solved in real-time, and provides multi-arm task-space coordination for both synchronous or asynchronous behaviors. Expand
Multi-Agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning
A hybrid algorithm of deep reinforcement learning (RL) and Force-based motion planning (FMP) to solve distributed motion planning problem in dense and dynamic environments and extends GA3C-CADRL algorithm to 3D environment. Expand
Harnessing Reinforcement Learning for Neural Motion Planning
This work proposes a modification of the popular DDPG RL algorithm that is tailored to motion planning domains, by exploiting the known model in the problem and the set of solved plans in the data, and shows that the algorithm can plan significantly faster on novel domains than off-the-shelf sampling based motion planners. Expand
PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-Based Planning
This work presents PRM-RL, a hierarchical method for long-range navigation task completion that combines sampling-based path planning with reinforcement learning (RL), and evaluates it on two navigation tasks with non-trivial robot dynamics. Expand
From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots
This work presents the first approach that learns a target-oriented end-to-end navigation model for a robotic platform, and demonstrates that the learned navigation model is directly transferable to previously unseen virtual and, more interestingly, real-world environments. Expand
dRRT*: Scalable and informed asymptotically-optimal multi-robot motion planning
This work identifies the conditions for convergence to optimal paths in multi-robot problems, which the prior method was not achieving and identifies the planner’s capability to solve problems involving multiple real-world robotic arms. Expand
Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
  • Michael Everett, Y. Chen, J. How
  • Computer Science, Engineering
  • 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2018
This work extends the previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules, and introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size. Expand
Deeply Informed Neural Sampling for Robot Motion Planning
A neural network-based adaptive sampler for motion planning called Deep Sampling-based Motion Planner (DeepSMP), which generates samples for SMPs and enhances their overall speed significantly while exhibiting efficient scalability to higher-dimensional problems. Expand
Continuous control with deep reinforcement learning
This work presents an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces, and demonstrates that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs. Expand
Motion Planning Networks
This work presents Motion Planning Networks (MPNet), a neural network-based novel planning algorithm that encodes the given workspaces directly from a point cloud measurement and generates the end-to-end collision-free paths for the given start and goal configurations. Expand