Research Analyzer
← Back ICRA 2026

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

Sourav Raxit, Abdullah Al Redwan Newaz, Paulo Padrao, Jose Fuentes, Leonardo Bobadilla

PDF

AI summary

Key figure (auto-extracted from paper)
The BOW Planner efficiently navigates robots in complex environments by combining dynamic velocity windows with constrained Bayesian optimization to achieve faster, safer, and more sample-efficient motion planning.
Motion Planning Bayesian Optimization Constrained Optimization Kinodynamic Planning Gaussian Processes Robot Navigation

Problem

Traditional motion planners struggle with kinodynamic constraints and high-dimensional objectives, making long-horizon optimization computationally expensive and slow.

Approach

BOW restricts control sampling to a short, dynamically reachable velocity window and uses constrained Bayesian optimization with Gaussian processes to efficiently identify safe, optimal control inputs.

Key results

  • Enhanced sample efficiency with fewer control evaluations
  • Direct integration of safety constraints into optimization
  • Reduced computation and trajectory planning times
  • Proven asymptotic convergence to near-optimal solutions

Why it matters

Enables real-time, safe, and scalable motion planning for complex robotic systems operating in cluttered or dynamically constrained environments.

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 lim- its, 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 ad- vancing 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/.

Index terms

Motion and Path Planning Collision Avoidance Nonholonomic Motion Planning

Related papers