Robust Global-Local Behavior Arbitration via Continuous Command Fusion Under LiDAR Errors
📰 ArXiv cs.AI
Robust arbitration module for autonomous driving systems fuses global and local controllers under LiDAR errors
Action Steps
- Develop a global reference-tracking controller based on Pure Pursuit
- Implement a reactive LiDAR-based Gap Follow controller
- Design a continuous command fusion module to arbitrate between the two controllers
- Test and evaluate the arbitration module under various LiDAR error scenarios
Who Needs to Know This
This research benefits autonomous driving system developers and engineers, particularly those working on modular systems that require coordination between global progress objectives and local safety-driven reactions
Key Insight
💡 Continuous command fusion can effectively arbitrate between global and local controllers in autonomous driving systems under imperfect sensing conditions
Share This
💡 Autonomous driving systems: robust arbitration module fuses global & local controllers under LiDAR errors
Key Takeaways
Robust arbitration module for autonomous driving systems fuses global and local controllers under LiDAR errors
Full Article
Title: Robust Global-Local Behavior Arbitration via Continuous Command Fusion Under LiDAR Errors
Abstract:
arXiv:2603.27273v1 Announce Type: cross 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 cont
Abstract:
arXiv:2603.27273v1 Announce Type: cross 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 cont
DeepCamp AI