Saved in:
Bibliographic Details
Main Authors: Chen, Hao, Wan, Weiwei, Matsushita, Masaki, Kotaka, Takeyuki, Harada, Kensuke
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.09772
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914645193785344
author Chen, Hao
Wan, Weiwei
Matsushita, Masaki
Kotaka, Takeyuki
Harada, Kensuke
author_facet Chen, Hao
Wan, Weiwei
Matsushita, Masaki
Kotaka, Takeyuki
Harada, Kensuke
contents A combined task-level reinforcement learning and motion planning framework is proposed in this paper to address a multi-class in-rack test tube rearrangement problem. At the task level, the framework uses reinforcement learning to infer a sequence of swap actions while ignoring robotic motion details. At the motion level, the framework accepts the swapping action sequences inferred by task-level agents and plans the detailed robotic pick-and-place motion. The task and motion-level planning form a closed loop with the help of a condition set maintained for each rack slot, which allows the framework to perform replanning and effectively find solutions in the presence of low-level failures. Particularly for reinforcement learning, the framework leverages a distributed deep Q-learning structure with the Dueling Double Deep Q Network (D3QN) to acquire near-optimal policies and uses an A${}^\star$-based post-processing technique to amplify the collected training data. The D3QN and distributed learning help increase training efficiency. The post-processing helps complete unfinished action sequences and remove redundancy, thus making the training data more effective. We carry out both simulations and real-world studies to understand the performance of the proposed framework. The results verify the performance of the RL and post-processing and show that the closed-loop combination improves robustness. The framework is ready to incorporate various sensory feedback. The real-world studies also demonstrated the incorporation.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09772
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robotic Test Tube Rearrangement Using Combined Reinforcement Learning and Motion Planning
Chen, Hao
Wan, Weiwei
Matsushita, Masaki
Kotaka, Takeyuki
Harada, Kensuke
Robotics
A combined task-level reinforcement learning and motion planning framework is proposed in this paper to address a multi-class in-rack test tube rearrangement problem. At the task level, the framework uses reinforcement learning to infer a sequence of swap actions while ignoring robotic motion details. At the motion level, the framework accepts the swapping action sequences inferred by task-level agents and plans the detailed robotic pick-and-place motion. The task and motion-level planning form a closed loop with the help of a condition set maintained for each rack slot, which allows the framework to perform replanning and effectively find solutions in the presence of low-level failures. Particularly for reinforcement learning, the framework leverages a distributed deep Q-learning structure with the Dueling Double Deep Q Network (D3QN) to acquire near-optimal policies and uses an A${}^\star$-based post-processing technique to amplify the collected training data. The D3QN and distributed learning help increase training efficiency. The post-processing helps complete unfinished action sequences and remove redundancy, thus making the training data more effective. We carry out both simulations and real-world studies to understand the performance of the proposed framework. The results verify the performance of the RL and post-processing and show that the closed-loop combination improves robustness. The framework is ready to incorporate various sensory feedback. The real-world studies also demonstrated the incorporation.
title Robotic Test Tube Rearrangement Using Combined Reinforcement Learning and Motion Planning
topic Robotics
url https://arxiv.org/abs/2401.09772