Technology Category
Planning, Routing, and Scheduling: Model-Based ReasoningHumans and AI: Human-Aware Planning and Behavior PredictionMultiagent Systems: Multiagent Planning
Decentralized Modeling of Vehicular Maneuvers and Interactions at Urban Junctions
🤖 AI Summary
Existing intersection modeling approaches struggle to jointly capture non-cooperative interactions and vehicle dynamics, often relying on predefined trajectories, centralized control, or strong cooperation assumptions—limiting applicability in mixed-autonomy traffic. This paper proposes a decentralized trajectory planning and control framework: an upper layer employs heuristic-guided graph search to generate reference trajectories, while a lower layer utilizes a predictive controller—taking acceleration and steering angle as inputs—for robust tracking. The framework explicitly couples vehicle dynamics with non-cooperative game-theoretic behavior, accommodating realistic constraints such as perception uncertainty and limited sensor range. Crucially, it operates without vehicle-to-vehicle communication or central coordination. Evaluated in signal-free intersections and roundabouts, the framework demonstrates high-fidelity, high-accuracy multi-vehicle interaction simulation, achieving balanced trade-offs among safety, traffic efficiency, and ride comfort.
Technology Category
Application Category
📝 Abstract
Modeling and evaluation of automated vehicles (AVs) in mixed-autonomy traffic is essential prior to their safe and efficient deployment. This is especially important at urban junctions where complex multi-agent interactions occur. Current approaches for modeling vehicular maneuvers and interactions at urban junctions have limitations in formulating non-cooperative interactions and vehicle dynamics within a unified mathematical framework. Previous studies either assume predefined paths or rely on cooperation and central controllability, limiting their realism and applicability in mixed-autonomy traffic. This paper addresses these limitations by proposing a modeling framework for trajectory planning and decentralized vehicular control at urban junctions. The framework employs a bi-level structure where the upper level generates kinematically feasible reference trajectories using an efficient graph search algorithm with a custom heuristic function, while the lower level employs a predictive controller for trajectory tracking and optimization. Unlike existing approaches, our framework does not require central controllability or knowledge sharing among vehicles. The vehicle kinematics are explicitly incorporated at both levels, and acceleration and steering angle are used as control variables. This intuitive formulation facilitates analysis of traffic efficiency, environmental impacts, and motion comfort. The framework's decentralized structure accommodates operational and stochastic elements, such as vehicles' detection range, perception uncertainties, and reaction delay, making the model suitable for safety analysis. Numerical and simulation experiments across diverse scenarios demonstrate the framework's capability in modeling accurate and realistic vehicular maneuvers and interactions at various urban junctions, including unsignalized intersections and roundabouts.
Problem
Research questions and friction points this paper is trying to address.
Modeling non-cooperative vehicle interactions at urban junctions
Decentralized trajectory planning for mixed-autonomy traffic
Incorporating vehicle kinematics without central controllability
Innovation
Methods, ideas, or system contributions that make the work stand out.
Decentralized bi-level framework for urban junctions
Graph search with custom heuristic for trajectories
Predictive controller for tracking and optimization
🔎 Similar Papers
No similar papers found.
