BOW: Bayesian Optimization over Windows for Motion Planning in Complex Environments

TL;DR

The paper presents the BOW Planner, a scalable Bayesian optimization-based motion planning algorithm that efficiently generates safe, near-optimal trajectories in complex environments, outperforming existing methods in speed and reliability.

Contribution

It introduces a novel constrained Bayesian optimization approach focused on planning windows, enabling rapid, safe motion planning with theoretical guarantees and practical effectiveness.

Findings

Substantial reduction in computation times compared to existing methods.

High sample efficiency and safety-aware optimization demonstrated in real-world tests.

Theoretical convergence to near-optimal solutions confirmed.

Abstract

This paper introduces the BOW Planner, a scalable motion planning algorithm designed to navigate robots through complex environments using constrained Bayesian optimization (CBO). Unlike traditional methods, which often struggle with kinodynamic constraints such as velocity and acceleration limits, the BOW Planner excels by concentrating on a planning window of reachable velocities and employing CBO to sample control inputs efficiently. This approach enables the planner to manage high-dimensional objective functions and stringent safety constraints with minimal sampling, ensuring rapid and secure trajectory generation. Theoretical analysis confirms the algorithm's asymptotic convergence to near-optimal solutions, while extensive evaluations in cluttered and constrained settings reveal substantial improvements in computation times, trajectory lengths, and solution times compared to existing techniques. Successfully deployed across various real-world robotic systems, the BOW Planner demonstrates its practical significance through exceptional sample efficiency, safety-aware optimization, and rapid planning capabilities, making it a valuable tool for advancing robotic applications. The BOW Planner is released as an open-source package and videos of real-world and simulated experiments are available at https://bow-web.github.io.