Pedestrian Vehicle Interaction

Pedestrian-vehicle interaction research focuses on improving safety and efficiency in shared spaces by understanding and predicting pedestrian behavior and driver responses. Current research employs various machine learning models, including neural networks (like LSTMs and convolutional models) and game-theoretic approaches, often incorporating data from diverse sources such as video analytics, LiDAR, and UWB sensors to create more robust and accurate predictive models. This work is crucial for advancing autonomous vehicle technology, enhancing traffic management strategies, and ultimately reducing pedestrian accidents. The development of comprehensive datasets and improved modeling techniques are key areas of ongoing investigation.