Saved in:
Bibliographic Details
Main Authors: Weiss, Trent, Kulkarni, Amar, Behl, Madhur
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.22937
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918152135245824
author Weiss, Trent
Kulkarni, Amar
Behl, Madhur
author_facet Weiss, Trent
Kulkarni, Amar
Behl, Madhur
contents A significant challenge in autonomous racing is to generate overtaking maneuvers. Racing agents must execute these maneuvers on complex racetracks with little room for error. Optimization techniques and graph-based methods have been proposed, but these methods often rely on oversimplified assumptions for collision-avoidance and dynamic constraints. In this work, we present an approach to trajectory synthesis based on an extension of the Differential Bayesian Filtering framework. Our approach for collision-free trajectory synthesis frames the problem as one of Bayesian Inference over the space of Composite Bezier Curves. Our method is derivative-free, does not require a spherical approximation of the vehicle footprint, linearization of constraints, or simplifying upper bounds on collision avoidance. We conduct a closed-loop analysis of DBF-MA and find it successfully overtakes an opponent in 87% of tested scenarios, outperforming existing methods in autonomous overtaking.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DBF-MA: A Differential Bayesian Filtering Planner for Multi-Agent Autonomous Racing Overtakes
Weiss, Trent
Kulkarni, Amar
Behl, Madhur
Robotics
A significant challenge in autonomous racing is to generate overtaking maneuvers. Racing agents must execute these maneuvers on complex racetracks with little room for error. Optimization techniques and graph-based methods have been proposed, but these methods often rely on oversimplified assumptions for collision-avoidance and dynamic constraints. In this work, we present an approach to trajectory synthesis based on an extension of the Differential Bayesian Filtering framework. Our approach for collision-free trajectory synthesis frames the problem as one of Bayesian Inference over the space of Composite Bezier Curves. Our method is derivative-free, does not require a spherical approximation of the vehicle footprint, linearization of constraints, or simplifying upper bounds on collision avoidance. We conduct a closed-loop analysis of DBF-MA and find it successfully overtakes an opponent in 87% of tested scenarios, outperforming existing methods in autonomous overtaking.
title DBF-MA: A Differential Bayesian Filtering Planner for Multi-Agent Autonomous Racing Overtakes
topic Robotics
url https://arxiv.org/abs/2509.22937