The pedestrians always want to avoid collision with others. A data-driven simulation model of collision avoidance behavior is proposed in this paper. In order to predict the walking speed and direction of pedestrians, the machine learning method is used to learn the movement rule of pedestrians from trajectory data. First, the features are selected based on the microscopic interaction analysis and we extract the features from trajectory data. Secondly, the decision tree model is used to predict the walking direction and speed of pedestrians and the simulation model is proposed to smooth the speed evolution. Finally, an experimental study is conducted to simulate the collision avoidance behavior of pedestrians. The experimental results show that the proposed simulation model can provide walking direction and speed decision strategy which contributes to the generation of the natural collision free path.
A Data Driven Simulation Model for Investigating Collision Avoidance Behavior of Pedestrians in Subway Stations
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Chapter : 52 ; 467-474
2022-02-23
8 pages
Article/Chapter (Book)
Electronic Resource
English
British Library Conference Proceedings | 2022
|Experimental study on pedestrians' collision avoidance
IEEE | 2014
|Collision Avoidance of Low Speed Autonomous Shuttles with Pedestrians
Springer Verlag | 2020
|