Paper Info
Title
A Social Force Based Pedestrian Motion Model Considering Multi-Pedestrian Interaction with a Vehicle.
Abstract
Pedestrian motion modeling in mixed traffic scenarios is crucial to the development of autonomous systems in transportation related applications. This work investigated how pedestrian motion is affected by surrounding pedestrians and vehicles, i.e., vehicle-pedestrian interaction. A social force based pedestrian motion model was proposed, in which the effect of surrounding pedestrians was improved and the effect of vehicles was newly designed. Variable constraints dependent on vehicle influence as well as nearby pedestrian density were imposed on the velocity and acceleration of the pedestrian motion. This work focuses on fundamental patterns of multi-pedestrian interaction with a low speed vehicle (front, back, and lateral interaction in open space). In other words, the application of the model is not restricted to specific scenarios such as crosswalks. Parameters of the proposed model were calibrated by the genetic algorithm (GA) based on trajectory data of the same vehicle-pedestrian interaction patterns from controlled experiments. The proposed model is able to simulate complex self-designed vehicle-pedestrian interaction scenarios. The effectiveness of the proposed model was validated by comparing the simulated trajectories with ground truth trajectories under the same initial conditions, and by evaluating the pedestrian behavior of avoiding vehicle in the simulation of self-designed scenarios.
Year
DOI
Venue
2020
10.1145/3373646
ACM Transactions on Spatial Algorithms and Systems
Keywords
Field
DocType
Pedestrian motion,genetic algorithm,social force,vehicle-pedestrian interaction
Pedestrian,Social force,Computer science,Artificial intelligence,Machine learning
Journal
Volume
Issue
ISSN
6
2
2374-0353
Citations 
PageRank 
References 
0
0.34
0
Authors
3
Name
Order
Citations
PageRank
Dongfang Yang1114.43
Ümit Özgüner21014166.59
Keith A. Redmill300.34