HALO: Fault-Tolerant Safety Architecture For High-Speed Autonomous Racing

2025-03-13

AI Summary

High-speed autonomous racing (>170 mph) poses severe safety risks due to subsystem failures in highly dynamic, multi-agent competitive environments. Method: This paper proposes HALO, a safety architecture tailored for such scenarios. HALO introduces a novel three-layer fault taxonomy—encompassing node health, data integrity, and behavioral safety—paired with corresponding closed-loop governance mechanisms. It integrates Failure Modes and Effects Analysis (FMEA), multi-granularity runtime monitoring, and state-machine-driven safety degradation strategies, while supporting embedded deployment and multi-vehicle cooperative validation. Contribution/Results: Evaluated in the Indy Autonomous Challenge (IAC) real-world racing trials, HALO successfully detected and mitigated dozens of representative fault classes, achieving zero safety-critical incidents. The architecture significantly enhances system safety robustness in dense, high-dynamic multi-vehicle racing settings.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

The field of high-speed autonomous racing has seen significant advances in recent years, with the rise of competitions such as RoboRace and the Indy Autonomous Challenge providing a platform for researchers to develop software stacks for autonomous race vehicles capable of reaching speeds in excess of 170 mph. Ensuring the safety of these vehicles requires the software to continuously monitor for different faults and erroneous operating conditions during high-speed operation, with the goal of mitigating any unreasonable risks posed by malfunctions in sub-systems and components. This paper presents a comprehensive overview of the HALO safety architecture, which has been implemented on a full-scale autonomous racing vehicle as part of the Indy Autonomous Challenge. The paper begins with a failure mode and criticality analysis of the perception, planning, control, and communication modules of the software stack. Specifically, we examine three different types of faults - node health, data health, and behavioral-safety faults. To mitigate these faults, the paper then outlines HALO safety archetypes and runtime monitoring methods. Finally, the paper demonstrates the effectiveness of the HALO safety architecture for each of the faults, through real-world data gathered from autonomous racing vehicle trials during multi-agent scenarios.

Problem

• Ensures safety in high-speed autonomous racing vehicles.
• Monitors and mitigates faults in software subsystems.
• Demonstrates effectiveness through real-world racing trials.

Innovation

• HALO safety architecture for autonomous racing
• Runtime monitoring for node, data, behavioral faults
• Real-world trials validate fault mitigation effectiveness