ST-pRRTC: Parallel Space-Time RRT-C with Adaptive Goal-Time Forests

2026-09-24

AI Summary

This study addresses the challenging problem of path planning in dynamic environments where target arrival times are unknown. We propose a spatiotemporal search framework built upon a shared forward tree and an adaptive backward goal-time forest. Probabilistic completeness is guaranteed through an interval root formula, while a root recycling strategy is designed to flexibly adjust the number of backward trees without discarding accumulated search progress. To achieve efficient computation, the framework integrates GPU parallel acceleration, spatiotemporal RRT-Connect, and adaptive sampling. Experimental results demonstrate that the proposed method significantly outperforms baselines such as ST-RRT* in terms of both first-solution time and final arrival time. Furthermore, its practical effectiveness is validated on a UR5e robotic manipulator tasked with avoiding moving drones.

Abstract

We propose ST-pRRTC, a GPU-parallel space- time RRT-Connect motion planner for problems with known obstacle trajectories and unspecified arrival time. Searching over many arrival times broadens temporal coverage but divides a finite planning budget among more backward trees. To address the challenge, ST-pRRTC builds a shared forward tree and an adaptive forest of backward goal-time trees. Its interval root formulation samples goal arrival times continuously and guarantees probabilistic completeness and asymptotic arrival- time optimality under the stated assumptions in a bounded time domain. The practical root recycling policy has no such guar- antees. It adapts a fixed number of backward trees, replacing later roots while retaining useful search progress. Experiments on three dynamic benchmarks show that both variants achieve lower mean first-solution times and earlier mean final arrivals than ST-RRT* and SI-RRT on problems solved by all compared methods. Further experiments demonstrate the benefit of recy- cling over broad arrival-time ranges. Real-robot demonstrations show root-recycling ST-pRRTC planning motions for a UR5e among moving Crazyflie quadrotors.

Problem

• motion planning
• space-time planning
• dynamic environments
• unspecified arrival time
• RRT-Connect

Innovation

• GPU-parallel motion planning
• Space-Time RRT-Connect
• Adaptive goal-time forests
• Interval root formulation
• Root recycling policy