Kino-PAX$^+$: Near-Optimal Massively Parallel Kinodynamic Sampling-based Motion Planner

TL;DR

Kino-PAX$^{+}$ is a massively parallel kinodynamic motion planner that guarantees near-optimal solutions with asymptotic guarantees, significantly outperforming existing serial and GPU-based planners in speed and solution quality.

Contribution

It introduces a novel massively parallel algorithm with asymptotic near-optimal guarantees for kinodynamic motion planning, decomposing serial operations into three parallel subroutines.

Findings

Finds solutions up to 1000 times faster than serial methods.

Achieves lower solution costs than state-of-the-art GPU planners.

Maintains probabilistic δ-robust near-optimality.

Abstract

Sampling-based motion planners (SBMPs) are widely used for robot motion planning with complex kinodynamic constraints in high-dimensional spaces, yet they struggle to achieve \emph{real-time} performance due to their serial computation design. Recent efforts to parallelize SBMPs have achieved significant speedups in finding feasible solutions; however, they provide no guarantees of optimizing an objective function. We introduce Kino-PAX$^{+}$, a massively parallel kinodynamic SBMP with asymptotic near-optimal guarantees. Kino-PAX$^{+}$ builds a sparse tree of dynamically feasible trajectories by decomposing traditionally serial operations into three massively parallel subroutines. The algorithm focuses computation on the most promising nodes within local neighborhoods for propagation and refinement, enabling rapid improvement of solution cost. We prove that, while maintaining probabilistic $\delta$-robust completeness, this focus on promising nodes ensures asymptotic $\delta$-robust near-optimality. Our results show that Kino-PAX$^{+}$ finds solutions up to three orders of magnitude faster than existing serial methods and achieves lower solution costs than a state-of-the-art GPU-based planner.