Traffic Rule
Traffic rule research focuses on ensuring autonomous vehicle (AV) compliance and safety by bridging the gap between human-understandable regulations and machine-interpretable instructions. Current efforts concentrate on formalizing traffic rules using temporal logic and large language models (LLMs) to enable automated reasoning and decision-making, often integrated with reinforcement learning (RL) for safe trajectory planning. These advancements leverage various deep learning architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs like LSTMs and GRUs), and graph neural networks (GNNs), to process sensor data and predict vehicle behavior for collision avoidance and rule adherence. The ultimate goal is to develop robust and reliable AV systems that safely navigate complex traffic scenarios while strictly adhering to all applicable regulations.
Papers
Data-driven Diffusion Models for Enhancing Safety in Autonomous Vehicle Traffic Simulations
Jinxiong Lu, Shoaib Azam, Gokhan Alcan, Ville Kyrki
Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM
Tianhui Cai, Yifan Liu, Zewei Zhou, Haoxuan Ma, Seth Z. Zhao, Zhiwen Wu, Jiaqi Ma
Next-gen traffic surveillance: AI-assisted mobile traffic violation detection system
Dila Dede, Mehmet Ali Sarsıl, Ata Shaker, Olgu Altıntaş, Onur Ergen
IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather
Furqan Ahmed Shaik, Abhishek Malreddy, Nikhil Reddy Billa, Kunal Chaudhary, Sunny Manchanda, Girish Varma