Global Tensor Motion Planning

TL;DR

Global Tensor Motion Planning (GTMP) is a GPU-compatible, tensor-based, batch motion planning algorithm that efficiently generates smooth, collision-free paths using a novel graph structure, suitable for large-scale robot learning.

Contribution

GTMP introduces a tensor-based, sampling-driven motion planning method with a novel multipartite graph structure, enabling efficient batch planning and smooth path generation.

Findings

GTMP demonstrates high computational efficiency on large datasets.

GTMP supports smooth spline planning without gradient optimization.

GTMP exhibits probabilistic completeness and scalability.

Abstract

Batch planning is increasingly necessary to quickly produce diverse and quality motion plans for downstream learning applications, such as distillation and imitation learning. This paper presents Global Tensor Motion Planning (GTMP) -- a sampling-based motion planning algorithm comprising only tensor operations. We introduce a novel discretization structure represented as a random multipartite graph, enabling efficient vectorized sampling, collision checking, and search. We provide a theoretical investigation showing that GTMP exhibits probabilistic completeness while supporting modern GPU/TPU. Additionally, by incorporating smooth structures into the multipartite graph, GTMP directly plans smooth splines without requiring gradient-based optimization. Experiments on lidar-scanned occupancy maps and the MotionBenchMarker dataset demonstrate GTMP's computation efficiency in batch planning compared to baselines, underscoring GTMP's potential as a robust, scalable planner for diverse applications and large-scale robot learning tasks.