Real-Time Stochastic Kinodynamic Motion Planning via Multiobjective Search on GPUs

TL;DR

This paper introduces PUMP, a GPU-accelerated multiobjective search algorithm for stochastic kinodynamic motion planning that efficiently finds low-cost, safe trajectories by evaluating a large number of plans in real-time.

Contribution

The paper presents a novel GPU-based multiobjective search method with a new particle-based collision probability approximation for efficient stochastic motion planning.

Findings

PUMP identifies solutions in approximately 100 ms.

It evaluates over 100,000 plans during exploration.

It achieves lower cost solutions for the same safety constraints.

Abstract

In this paper we present the PUMP (Parallel Uncertainty-aware Multiobjective Planning) algorithm for addressing the stochastic kinodynamic motion planning problem, whereby one seeks a low-cost, dynamically-feasible motion plan subject to a constraint on collision probability (CP). To ensure exhaustive evaluation of candidate motion plans (as needed to tradeoff the competing objectives of performance and safety), PUMP incrementally builds the Pareto front of the problem, accounting for the optimization objective and an approximation of CP. This is performed by a massively parallel multiobjective search, here implemented with a focus on GPUs. Upon termination of the exploration phase, PUMP searches the Pareto set of motion plans to identify the lowest cost solution that is certified to satisfy the CP constraint (according to an asymptotically exact estimator). We introduce a novel particle-based CP approximation scheme, designed for efficient GPU implementation, which accounts for dependencies over the history of a trajectory execution. We present numerical experiments for quadrotor planning wherein PUMP identifies solutions in ~100 ms, evaluating over one hundred thousand partial plans through the course of its exploration phase. The results show that this multiobjective search achieves a lower motion plan cost, for the same CP constraint, compared to a safety buffer-based search heuristic and repeated RRT trials.