This describes a joint Michigan/Berkeley project to develop technology for robust traffic monitoring and automated vehicle control using decision theory and probability. It shows that high-level traffic monitoring situations can be modeled using modern techniques, and that solving such models in real time is computationally feasible. Models were developed that infer the intended behavior of vehicles in traffic based on movement patterns and highway tactics (e.g., lane changes). In addition to their use in traffic monitoring (e.g., for gathering statistics of driver behavior), plan recognition models are indispensable for in-vehicle applications of several sorts--for any task in which it is crucial to anticipate movements of other vehicles. Models were developed and encoded using commercially available Hugin(TM) software. Existing algorithms, with some enhancements developed as part of the project, were used for all of the models. They can be solved without prohibitive computational resources; real-time performance is easily achievable using hardware based on Pentium-class processors. The capability has been demonstrated using Hugin(TM) in a standalone setup as well as in a driving simulator integrated with the SmartPATH animation system for real-time visualization of traffic scenarios.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Decision-theoretic reasoning for traffic monitoring and vehicle control

    Wellman, M.P. / Chao-Lin Liu / Pynadath, D. et al. | IEEE | 1995


    Decision-Theoretic Reasoning for Traffic Monitoring and Vehicle Control

    Wellman, M. / Liu, C. / Pynadath, D. et al. | British Library Conference Proceedings | 1995


    Dynamic Game Theoretic Electric Vehicle Decision Making

    Ouyang, Qianyu / Jia, Xianzhe | SAE Technical Papers | 2024


    Decision fusion and reasoning for traffic sign recognition

    Meuter, Mirko / Muller-Schneiders, Stefan / Nunny, Christian et al. | IEEE | 2010


    Adaptive Game-Theoretic Decision Making for Autonomous Vehicle Control at Roundabouts

    Tian, Ran / Li, Sisi / Li, Nan et al. | ArXiv | 2018

    Free access