Consensus-Aware AV Behavior: Trade-offs Between Safety, Interaction, and Performance in Mixed Urban Traffic

2025-05-07

AI Summary

In mixed-traffic urban environments, autonomous vehicles (AVs) must jointly optimize safety, interaction quality, and traffic efficiency—objectives that frequently conflict. Method: This work pioneers the formalization of “traffic system consensus” as a quantifiable multi-dimensional trade-off problem. Leveraging high-fidelity trajectory data from TGSIM, we empirically evaluate AV interactions with human-driven vehicles and vulnerable road users (VRUs) using integrated metrics—including time-to-collision (TTC), post-encroachment time (PET), dynamic deceleration rate, headway time, and string stability. Contribution/Results: We find that only 1.63% of frames simultaneously satisfy all three objectives, exposing the fundamental limitations of single-objective optimization paradigms. To address this, we propose a consensus-aware cooperative trade-off decision framework and open-source a complete analytical toolchain, establishing a new, reproducible, and verifiable benchmark for system-level AV evaluation.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Adversarial Agents
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Transportation systems have long been shaped by complexity and heterogeneity, driven by the interdependency of agent actions and traffic outcomes. The deployment of automated vehicles (AVs) in such systems introduces a new challenge: achieving consensus across safety, interaction quality, and traffic performance. In this work, we position consensus as a fundamental property of the traffic system and aim to quantify it. We use high-resolution trajectory data from the Third Generation Simulation (TGSIM) dataset to empirically analyze AV and human-driven vehicle (HDV) behavior at a signalized urban intersection and around vulnerable road users (VRUs). Key metrics, including Time-to-Collision (TTC), Post-Encroachment Time (PET), deceleration patterns, headways, and string stability, are evaluated across the three performance dimensions. Results show that full consensus across safety, interaction, and performance is rare, with only 1.63% of AV-VRU interaction frames meeting all three conditions. These findings highlight the need for AV models that explicitly balance multi-dimensional performance in mixed-traffic environments. Full reproducibility is supported via our open-source codebase on https://github.com/wissamkontar/Consensus-AV-Analysis.

Problem

• Balancing safety, interaction, and performance in AV-HDV mixed traffic
• Quantifying consensus in urban traffic using empirical trajectory data
• Addressing rare full consensus in AV-VRU interactions

Innovation

• Uses high-resolution trajectory data for analysis
• Evaluates key metrics across safety and performance
• Proposes AV models balancing multi-dimensional performance