🤖 AI Summary
This work addresses the challenge of coordinating global path tracking and local obstacle avoidance under noisy, delayed, or missing LiDAR perception to ensure the safety and robustness of autonomous driving systems. The authors propose a ROS 2-native continuous gating fusion mechanism that dynamically weights Ackermann steering commands from a Pure Pursuit global controller and a LiDAR Gap Follow local controller using a PPO-trained policy network operating on compact perceptual features, complemented by a safety verification module. This approach enables interpretable behavior coordination without modifying the underlying controllers and introduces a custom LiDAR error injection protocol for systematic robustness evaluation. Experiments demonstrate that, in close-proximity overtaking scenarios, the method significantly improves safety success rates over a lightweight predictive baseline as perception errors intensify, while maintaining real-time control performance.
📝 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.