RoboArm-NMP: a Learning Environment for Neural Motion Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jurgenson, Tom, Sudry, Matan, Avineri, Gal, Tamar, Aviv
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910459255324672
author Jurgenson, Tom
Sudry, Matan
Avineri, Gal
Tamar, Aviv
author_facet Jurgenson, Tom
Sudry, Matan
Avineri, Gal
Tamar, Aviv
contents We present RoboArm-NMP, a learning and evaluation environment that allows simple and thorough evaluations of Neural Motion Planning (NMP) algorithms, focused on robotic manipulators. Our Python-based environment provides baseline implementations for learning control policies (either supervised or reinforcement learning based), a simulator based on PyBullet, data of solved instances using a classical motion planning solver, various representation learning methods for encoding the obstacles, and a clean interface between the learning and planning frameworks. Using RoboArm-NMP, we compare several prominent NMP design points, and demonstrate that the best methods mostly succeed in generalizing to unseen goals in a scene with fixed obstacles, but have difficulty in generalizing to unseen obstacle configurations, suggesting focus points for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16335
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RoboArm-NMP: a Learning Environment for Neural Motion Planning
Jurgenson, Tom
Sudry, Matan
Avineri, Gal
Tamar, Aviv
Robotics
Machine Learning
We present RoboArm-NMP, a learning and evaluation environment that allows simple and thorough evaluations of Neural Motion Planning (NMP) algorithms, focused on robotic manipulators. Our Python-based environment provides baseline implementations for learning control policies (either supervised or reinforcement learning based), a simulator based on PyBullet, data of solved instances using a classical motion planning solver, various representation learning methods for encoding the obstacles, and a clean interface between the learning and planning frameworks. Using RoboArm-NMP, we compare several prominent NMP design points, and demonstrate that the best methods mostly succeed in generalizing to unseen goals in a scene with fixed obstacles, but have difficulty in generalizing to unseen obstacle configurations, suggesting focus points for future research.
title RoboArm-NMP: a Learning Environment for Neural Motion Planning
topic Robotics
Machine Learning
url https://arxiv.org/abs/2405.16335