Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions

TL;DR

This paper introduces SPARK and FLAME, two experience-based sampling frameworks that leverage workspace decompositions to improve motion planning efficiency in high-dimensional robotic manipulators, demonstrating better generalization and performance with limited data.

Contribution

The paper presents novel workspace decomposition-based sampling methods, SPARK and FLAME, that enhance experience reuse and generalization in high-dimensional motion planning tasks.

Findings

SPARK and FLAME improve planning efficiency in complex environments.

Both methods generalize well with limited training examples.

They outperform prior approaches in diverse manipulation tasks.

Abstract

Earlier work has shown that reusing experience from prior motion planning problems can improve the efficiency of similar, future motion planning queries. However, for robots with many degrees-of-freedom, these methods exhibit poor generalization across different environments and often require large datasets that are impractical to gather. We present SPARK and FLAME , two experience-based frameworks for sampling-based planning applicable to complex manipulators in 3 D environments. Both combine samplers associated with features from a workspace decomposition into a global biased sampling distribution. SPARK decomposes the environment based on exact geometry while FLAME is more general, and uses an octree-based decomposition obtained from sensor data. We demonstrate the effectiveness of SPARK and FLAME on a Fetch robot tasked with challenging pick-and-place manipulation problems. Our approaches can be trained incrementally and significantly improve performance with only a handful of examples, generalizing better over diverse tasks and environments as compared to prior approaches.