STCLocker: Deadlock Avoidance Testing for Autonomous Driving Systems

2025-06-30

AI Summary

Autonomous driving systems (ADS) in multi-vehicle cooperative scenarios are prone to deadlock—characterized by cyclic waiting that causes motion planning failure—yet existing testing methods lack targeted deadlock detection and stimulation capabilities. Method: This paper proposes STCLocker, the first spatiotemporal conflict-guided testing method specifically designed to evaluate ADS deadlock avoidance capability. STCLocker introduces a dedicated black-box deadlock detection and feedback framework, actively inducing inter-vehicle resource contention through spatial right-of-way competition modeling and temporal synchronized-arrival control to efficiently generate reproducible deadlock scenarios. Contribution/Results: Evaluated on Roach and OpenCDA platforms, STCLocker significantly increases the number of generated deadlock scenarios compared to baseline methods. It enables the first systematic, scalable stress testing of cooperative safety for ADS, bridging a critical gap in evaluating real-world multi-agent coordination robustness.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Adversarial Agents
• Intelligent Robots: Multi-Robot Systems

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

Autonomous Driving System (ADS) testing is essential to ensure the safety and reliability of autonomous vehicles (AVs) before deployment. However, existing techniques primarily focus on evaluating ADS functionalities in single-AV settings. As ADSs are increasingly deployed in multi-AV traffic, it becomes crucial to assess their cooperative performance, particularly regarding deadlocks, a fundamental coordination failure in which multiple AVs enter a circular waiting state indefinitely, resulting in motion planning failures. Despite its importance, the cooperative capability of ADSs to prevent deadlocks remains insufficiently underexplored. To address this gap, we propose the first dedicated Spatio-Temporal Conflict-Guided Deadlock Avoidance Testing technique, STCLocker, for generating DeadLock Scenarios (DLSs), where a group of AVs controlled by the ADS under test are in a circular wait state. STCLocker consists of three key components: Deadlock Oracle, Conflict Feedback, and Conflict-aware Scenario Generation. Deadlock Oracle provides a reliable black-box mechanism for detecting deadlock cycles among multiple AVs within a given scenario. Conflict Feedback and Conflict-aware Scenario Generation collaborate to actively guide AVs into simultaneous competition over spatial conflict resources (i.e., shared passing regions) and temporal competitive behaviors (i.e., reaching the conflict region at the same time), thereby increasing the effectiveness of generating conflict-prone deadlocks. We evaluate STCLocker on two types of ADSs: Roach, an end-to-end ADS, and OpenCDA, a module-based ADS supporting cooperative communication. Experimental results show that, on average, STCLocker generates more DLS than the best-performing baseline.

Problem

• Assessing cooperative performance of Autonomous Driving Systems in multi-AV traffic
• Detecting and preventing deadlocks in multi-AV scenarios
• Generating conflict-prone deadlock scenarios for ADS testing

Innovation

• Spatio-Temporal Conflict-Guided Deadlock Avoidance Testing
• Deadlock Oracle detects deadlock cycles
• Conflict-aware Scenario Generation increases deadlocks