English

RoboArm-NMP: a Learning Environment for Neural Motion Planning

Robotics 2024-05-28 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2405.16335,
  title  = {RoboArm-NMP: a Learning Environment for Neural Motion Planning},
  author = {Tom Jurgenson and Matan Sudry and Gal Avineri and Aviv Tamar},
  journal= {arXiv preprint arXiv:2405.16335},
  year   = {2024}
}
R2 v1 2026-06-28T16:40:24.988Z