CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution

2025-03-03

AI Summary

Real-time management of complex urban traffic anomalies—such as phantom congestion, intersection gridlock, and accident liability assessment—faces critical bottlenecks in timely response, weak causal attribution, and non-executable mitigation strategies. Method: This paper proposes a chain-of-thought (CoT)-driven vision-language model (VLM) framework. It innovatively integrates CoT reasoning into a multimodal VLM to enable an end-to-end闭环 governance pipeline: from anomaly perception and causal attribution to generation of interpretable, executable control policies. An instruction translation module bridges natural language policies to CARLA-based simulation control via semantic mapping. Contribution/Results: Evaluated in closed-loop CARLA simulations, the framework significantly improves anomaly detection accuracy and response latency. It is the first work to empirically validate the feasibility and effectiveness of VLMs for autonomous traffic management systems, demonstrating robust cross-modal reasoning and actionable policy synthesis.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Large Vision Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

With the acceleration of urbanization, modern urban traffic systems are becoming increasingly complex, leading to frequent traffic anomalies. These anomalies encompass not only common traffic jams but also more challenging issues such as phantom traffic jams, intersection deadlocks, and accident liability analysis, which severely impact traffic flow, vehicular safety, and overall transportation efficiency. Currently, existing solutions primarily rely on manual intervention by traffic police or artificial intelligence-based detection systems. However, these methods often suffer from response delays and inconsistent management due to inadequate resources, while AI detection systems, despite enhancing efficiency to some extent, still struggle to handle complex traffic anomalies in a real-time and precise manner. To address these issues, we propose CoT-VLM4Tar: (Chain of Thought Visual-Language Model for Traffic Anomaly Resolution), this innovative approach introduces a new chain-of-thought to guide the VLM in analyzing, reasoning, and generating solutions for traffic anomalies with greater reasonable and effective solution, and to evaluate the performance and effectiveness of our method, we developed a closed-loop testing framework based on the CARLA simulator. Furthermore, to ensure seamless integration of the solutions generated by the VLM with the CARLA simulator, we implement an itegration module that converts these solutions into executable commands. Our results demonstrate the effectiveness of VLM in the resolution of real-time traffic anomalies, providing a proof-of-concept for its integration into autonomous traffic management systems.

Problem

• Addresses complex urban traffic anomalies like phantom jams and deadlocks
• Improves real-time and precise AI-based traffic anomaly resolution
• Integrates VLM solutions with CARLA simulator for autonomous traffic management

Innovation

• Chain-of-Thought guided Vision-Language Model
• Closed-loop testing with CARLA simulator
• Integration module for executable commands