Decentralized Opinion-Integrated Decision making at Unsignalized Intersections via Signed Networks
2026-04-10 • Multiagent Systems
Multiagent SystemsRobotics
AI summaryⓘ
The authors address how self-driving cars can make decisions together at intersections without traffic lights or a central controller. They created a system where cars share their intentions through two special networks to help decide whether to go or yield. This system uses math to predict if a car can safely move and then commits to a decision that influences nearby cars. Their approach works well in tests, avoiding collisions and improving traffic flow compared to just letting cars go in the order they arrive. It works for different types of intersection conflicts without needing complex calculations.
decentralized decision makingautonomous vehiclesunsignalized intersectionsopinion dynamicssigned networkscollision avoidancevelocity optimizationcommitment modelconflict topologytraffic coordination
Authors
Bhaskar Varma, Ying Shuai Quan, Karl D. von Ellenrieder, Paolo Falcone
Abstract
In this letter, we consider the problem of decentralized decision making among connected autonomous vehicles at unsignalized intersections, where existing centralized approaches do not scale gracefully under mixed maneuver intentions and coordinator failure. We propose a closed-loop opinion-dynamic decision model for intersection coordination, where vehicles exchange intent through dual signed networks: a conflict topology based communication network and a commitment-driven belief network that enable cooperation without a centralized coordinator. Continuous opinion states modulate velocity optimizer weights prior to commitment; a closed-form predictive feasibility gate then freezes each vehicle's decision into a GO or YIELD commitment, which propagates back through the belief network to pre-condition neighbor behavior ahead of physical conflicts. Crossing order emerges from geometric feasibility and arrival priority without the use of joint optimization or a solver. The approach is validated across three scenarios spanning fully competitive, merge, and mixed conflict topologies. The results demonstrate collision-free coordination and lower last-vehicle exit times compared to first come first served (FCFS) in all conflict non-trivial configurations.