LISA: Cognitive Arbitration for Signal-Free Autonomous Intersection Management

2026-05-12

AI Summary

This study addresses the challenges of right-of-way conflicts, heterogeneous priority rules, and real-time motion coordination faced by autonomous vehicles at unsignalized intersections. The authors propose LISA, a novel framework that leverages a large language model (LLM) as its core decision-making engine to cognitively arbitrate vehicle intent declarations and synthesize priorities, queueing pressure, and energy-efficiency preferences into real-time speed guidance and intersection scheduling strategies. By integrating reasoning-based optimization, LISA overcomes the inherent latency limitations of LLMs while eliminating reliance on traffic signals or explicit intent communication. Experimental results demonstrate significant improvements over baseline methods: average control latency is reduced by 89.1%, waiting time decreases by 93% under near-saturation traffic conditions, queue lengths are shortened by 60.6%, fuel consumption drops by 48.8%, and intent satisfaction achieves 86.2%.

Abstract

Large language models (LLMs) show strong potential for Intelligent Transportation Systems (ITS), particularly in tasks requiring situational reasoning and multi-agent coordination. These capabilities make them well suited for cooperative driving, where rule-based approaches struggle in complex and dynamic traffic environments. Intersection management remains especially challenging due to conflicting right-of-way demands, heterogeneous vehicle priorities, and vehicle-specific kinematic constraints that must be resolved in real time. However, existing approaches typically use LLMs as auxiliary components on top of signal-based systems rather than as primary decision-makers. Signal controllers remain vehicle-agnostic, reservation-based methods lack intent awareness, and recent LLM-based systems still depend on signal infrastructure. In addition, LLM inference latency limits their use in sub-second control settings. We propose LISA (LLM-Based Intent-Driven Speed Advisory), a signal-free cognitive arbitration framework for autonomous intersection management. LISA uses an LLM to reason over declared vehicle intents, incorporating priority classes, queue pressure, and energy preferences. We evaluate LISA against fixed-cycle control, SCATS, AIM, and GLOSA across varying traffic loads. Results show that LISA reduces mean control delay by up to 89.1% and maintains Level of Service C while all non-LLM baselines degrade to Level of Service F. Under near-saturated demand, LISA reduces mean waiting time by 93% and peak queue length by 60.6% relative to fixed-cycle control. It also lowers fuel consumption by up to 48.8% and achieves 86.2% intent satisfaction, compared to 61.2% for the best non-LLM method. These results demonstrate that LLM-based reasoning can enable real-time, signal-free intersection management.

Problem

• autonomous intersection management
• signal-free control
• multi-agent coordination
• vehicle intent
• real-time decision-making

Innovation

• LLM-based arbitration
• signal-free intersection management
• intent-driven control
• cognitive reasoning
• autonomous driving coordination