Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions
This work addresses the challenge of efficient motion planning for complex manipulators in 3D environments, offering incremental training and better generalization over diverse tasks compared to prior methods, though it appears incremental as it builds on existing experience-based planning approaches.
The authors tackled the problem of poor generalization and high data requirements in experience-based motion planning for high-DOF robots by introducing SPARK and FLAME, two frameworks that combine samplers from workspace decompositions into biased sampling distributions, demonstrating improved performance with only a few examples on a Fetch robot in pick-and-place tasks.
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.