RoboArm-NMP: a Learning Environment for Neural Motion Planning

TL;DR

RoboArm-NMP is a comprehensive Python-based environment for evaluating neural motion planning algorithms for robotic manipulators, facilitating comparisons and highlighting challenges in generalization to new obstacle configurations.

Contribution

It introduces RoboArm-NMP, a new environment with baseline implementations, simulation tools, and data for advancing neural motion planning research.

Findings

Best methods generalize to unseen goals with fixed obstacles

Difficulty in generalizing to new obstacle configurations

Provides a platform for systematic evaluation of NMP algorithms

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.