Event-Triggered Pinning Control for Cooperative Ramp Merging in Mixed Traffic via Graph Reinforcement Learning

Abstract

This paper proposes event-triggered pinning graph reinforcement learning (EPGRL) for cooperative ramp merging in mixed traffic with connected and automated vehicles (CAVs) and human-driven vehicles. EPGRL represents vehicle interactions as a time-varying directed graph and uses a dual-stream graph encoder with temporal updating to capture evolving traffic couplings. A Lyapunov-based trigger activates cooperation when a stability-oriented surrogate index indicates loss of contractivity, while topology-aware pinning allocates control to influential CAVs. A PPO policy generates longitudinal and lateral actions, which are filtered by a safety shield. SUMO experiments across traffic demands and CAV penetration rates show that EPGRL improves travel time, fuel use, CO2 emissions, and system-level time-to-collision relative to uncontrolled, infrastructure-based, and learning-based baselines. Event-timing and spatial analyses characterize the distribution of cooperative updates, while the control-update reduction rate ranges from 73.1% to 79.8% across representative settings. Ablation experiments further show that graph modeling, instability-aware triggering, and pinning selection make complementary contributions. These results indicate that selective, state-dependent cooperation can balance mobility, safety, energy use, and communication cost in simulated mixed-traffic merging.