Decentralized Opinion-Integrated Decision making at Unsignalized Intersections via Signed Networks

arXiv cs.RO / 4/13/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses decentralized coordination for connected autonomous vehicles at unsignalized intersections, focusing on scalability limits of centralized methods under mixed intentions and potential coordinator failure.
It proposes a closed-loop, opinion-dynamic decision model where vehicles communicate intent via two dual signed networks: a conflict-topology network and a commitment-driven belief network.
Vehicles use continuous opinion states to modulate their velocity optimizer weights, then apply a closed-form predictive feasibility gate to commit to GO or YIELD, which propagates through the belief network to shape neighbors’ behavior before physical conflicts.
The crossing order is derived from geometric feasibility and arrival priority without joint optimization or external solvers.
Experiments across three intersection scenarios (competitive, merge, and mixed conflict topologies) show collision-free coordination and improved last-vehicle exit times versus FCFS in non-trivial conflict configurations.

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.