Robust Global-Local Behavior Arbitration via Continuous Command Fusion Under LiDAR Errors

TL;DR

This paper introduces a ROS2-based arbitration module that fuses global and local controllers for autonomous driving, enhancing robustness against LiDAR sensor errors through continuous command fusion and safety checks.

Contribution

It presents a novel continuous command fusion approach using PPO-trained policy for robust behavior arbitration under sensor imperfections in autonomous driving.

Findings

Achieved safe success rates under LiDAR noise and dropout conditions.

Demonstrated improved robustness compared to a sampling-based baseline.

Provided real-time controller runtime analysis under sensing stress.

Abstract

Modular autonomous driving systems must coordinate global progress objectives with local safety-driven reactions under imperfect sensing and strict real-time constraints. This paper presents a ROS2-native arbitration module that continuously fuses the outputs of two unchanged and interpretable controllers: a global reference-tracking controller based on Pure Pursuit and a reactive LiDAR-based Gap Follow controller. At each control step, both controllers propose Ackermann commands, and a PPO-trained policy predicts a continuous gate from a compact feature observation to produce a single fused drive command, augmented with practical safety checks. For comparison under identical ROS topic inputs and control rate, we implement a lightweight sampling-based predictive baseline. Robustness is evaluated using a ROS2 impairment protocol that injects LiDAR noise, delay, and dropout, and additionally sweeps forward-cone false short-range outliers. In a repeatable close-proximity passing scenario, we report safe success and failure rates together with per-step end-to-end controller runtime as sensing stress increases. The study is intended as a command-level robustness evaluation in a modular ROS2 setting, not as a replacement for planning-level interaction reasoning.