6 papers
Selective Cooperative Perception via Blind Spot Reasoning and Agentic Dialogue with Vision-Language Models
Chengyuan Ma, Shixiao Liang, Hangyu Li +6
Real-time cooperative perception (CP) in multi-agent traffic environments is highly resource-intensive, which posing scalability challenges for large-scale deployment. Efficiency c…
GEMS-RAG: Graph-grounded Engineering Multimodal Standards Retrieval-Augmented Generation
Abdul Hannan Azad, Irvin Wang, Jiwan Jiang +6
Engineering standards are challenging knowledge sources for large language models (LLMs) because they are hierarchical, multimodal, and densely connected through figures, tables, c…
SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control
Jiaxi Liu, Keshu Wu, Weizhe Tang +5
Temporary traffic control redirects vehicles through work zones, requiring automated vehicles to connect an interpretation of the visible devices to a continuous passing path. Geom…
Physics-Informed Koopman Learning for Data-Efficient System Identification of Automated Vehicle Dynamics
Hangyu Li, Yiming Meng, Zhaohui Liang +8
Understanding how a particular automated vehicle reacts to nearby traffic can improve motion prediction, control development, traffic simulation, and safety evaluation. However, co…
Real-Time Lane-Level Crash Detection on Freeways Using Sparse Telematics Data
Shixiao Liang, Chengyuan Ma, Pei Li +7
Real-time traffic crash detection is critical in intelligent transportation systems because traditional crash notifications often suffer delays and lack specific, lane-level locati…
CATS-V2V: A Real-World Vehicle-to-Vehicle Cooperative Perception Dataset with Complex Adverse Traffic Scenarios
Hangyu Li, Bofeng Cao, Zhaohui Liang +16
Vehicle-to-Vehicle (V2V) cooperative perception has great potential to enhance autonomous driving performance by overcoming perception limitations in complex adverse traffic scenar…