Artificial Intelligence Research / Methodologies Artificial intelligence enables INSPIRE Lab to learn from data, reason about complex systems, and make decisions across transportation and energy infrastructure. We develop deep reinforcement learning, large language models, and data-mining frameworks to extract actionable intelligence from large-scale infrastructure data. Key Approaches Deep Reinforcement Learning Network-aware policy learning for traffic control under uncertainty. Large Language Models Semantic reasoning over driving behavior and infrastructure decisions. Data Mining & Behavioral Analytics Pattern discovery from large-scale charging, mobility, and operational data. Featured Publications arXiv · 2026 LLM-MLFFN: Multi-Level Autonomous Driving Behavior Feature Fusion via Large Language Model Li, Wang, Cheng, Machineni, Guo, Chen, Jiao & Claudel arXiv · 2025 SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identification Li & Guo Transportmetrica B · 2025 Optimal Speed Limit Control for Network Mobility and Safety: A TD3 Approach Afifah & Guo Full Publication List → Highlighted Projects PI USDOT · Safer-Sim UTC Distributed Reinforcement Learning for Optimal Speed Limit Control Over Network with Partial Observability
