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.
@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}
}