Yanni Ju

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.

Traffic sensors provide real-time measurements of current traffic conditions, whereas traffic management applications require forecasts of future traffic speed or flow. This study considers the incremental expansion of an operating sensor network, in which a pre-trained network-level forecasting model must predict traffic states at sensor locations that were absent during training. Many spatio-temporal graph neural networks rely on sensor-specific embeddings and graph connections learned from data-rich training networks. These representations are undefined for previously unseen locations, limiting the direct application of pre-trained adaptive-graph forecasters during sensor-network expansion. To address this cold-start problem, we propose support-conditioned sensor-adaptive meta-graph learning (SC-SAMG), which derives target-node representations and spatial dependencies from a short support period. The framework combines a support-set encoder, a task-specific graph learner, and first-order meta-learning to adapt the network-level forecaster using one to seven days of target observations. Experiments on four traffic benchmarks evaluate forecasts of speed or flow over the next 15–60 min under a leakage-controlled held-out-node protocol. SC-SAMG consistently outperforms fine-tuned gated recurrent unit (GRU), adaptive graph convolutional recurrent network (AGCRN), and diffusion convolutional recurrent neural network (DCRNN) baselines. It reduces mean absolute error (MAE) by up to 11% relative to the adaptive-graph baseline and by up to 7% relative to the diffusion convolutional baseline. These results demonstrate the potential of support-conditioned graph adaptation for incorporating previously unseen sensor locations into existing network-level traffic forecasting systems.