LEGO: Leveraging Experience in Roadmap Generation for Sampling-Based Planning
This work addresses motion planning challenges for robots, such as in robot arm scenarios, by enhancing roadmap generation, though it appears incremental as it builds on prior learning-based approaches.
The paper tackles the problem of generating sparse roadmaps for sampling-based motion planning by leveraging prior experience, and it introduces LEGO, an algorithm that improves performance over existing methods by training with bottleneck and diverse samples, achieving significant gains in evaluation.
We consider the problem of leveraging prior experience to generate roadmaps in sampling-based motion planning. A desirable roadmap is one that is sparse, allowing for fast search, with nodes spread out at key locations such that a low-cost feasible path exists. An increasingly popular approach is to learn a distribution of nodes that would produce such a roadmap. State-of-the-art is to train a conditional variational auto-encoder (CVAE) on the prior dataset with the shortest paths as target input. While this is quite effective on many problems, we show it can fail in the face of complex obstacle configurations or mismatch between training and testing. We present an algorithm LEGO that addresses these issues by training the CVAE with target samples that satisfy two important criteria. Firstly, these samples belong only to bottleneck regions along near-optimal paths that are otherwise difficult-to-sample with a uniform sampler. Secondly, these samples are spread out across diverse regions to maximize the likelihood of a feasible path existing. We formally define these properties and prove performance guarantees for LEGO. We extensively evaluate LEGO on a range of planning problems, including robot arm planning, and report significant gains over heuristics as well as learned baselines.