Problem
Research questions and friction points this paper is trying to address.
Develops automated lane merging planning framework
Models vehicle interactions using game theory
Enhances traffic efficiency in dense scenarios
Automated Lane Merging via Game Theory and Branch Model Predictive Control
🤖 AI Summary
This work addresses the safety and efficiency challenges of multi-vehicle cooperative lane merging under dense traffic conditions. Methodologically, it formulates merging as a matrix-game-driven gap selection process and proposes a behavior-motion co-planning framework. It introduces the first branch-model predictive control (BMPC) formulation that unifies Nash and Stackelberg equilibria to explicitly model strategic uncertainty of surrounding vehicles. A tree-structured, perception-aware numerical solver is designed to ensure both high-fidelity interaction modeling and real-time computational performance. Experimental evaluation on real-world traffic datasets demonstrates significant improvements in merging success rate, safety (e.g., reduced collision risk and hard braking), and traffic throughput. The implementation is publicly available as open-source code.
📝 Abstract
We propose an integrated behavior and motion planning framework for the lane-merging problem. The behavior planner combines search-based planning with game theory to model vehicle interactions and plan multi-vehicle trajectories. Inspired by human drivers, we model the lane-merging problem as a gap selection process and determine the appropriate gap by solving a matrix game. Moreover, we introduce a branch model predictive control (BMPC) framework to account for the uncertain equilibrium strategies adopted by the surrounding vehicles, including Nash and Stackelberg strategies. A tailored numerical solver is developed to enhance computational efficiency by exploiting the tree structure inherent in BMPC. Finally, we validate our proposed integrated planner using real traffic data and demonstrate its effectiveness in handling interactions in dense traffic scenarios. The code is publicly available at: https://github.com/SailorBrandon/GT-BMPC.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Game theory for vehicle interactions
Branch model predictive control
Matrix game for gap selection
🔎 Similar Papers
No similar papers found.
