Forecasting Interactive Dynamics of Pedestrians with Fictitious Play

• Published in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 4636 - 4644
• Main Authors: Wei-Chiu Ma, De-An Huang, Namhoon Lee, Kitani, Kris M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2017
• Subjects: Computational modeling; Dynamics; Forecasting; Game theory; Predictive models; Trajectory; Visualization

We develop predictive models of pedestrian dynamics by encoding the coupled nature of multi-pedestrian interaction using game theory and deep learning-based visual analysis to estimate person-specific behavior parameters. We focus on predictive models since they are important for developing interact...