2-D pedestrian motion prediction modeling in urban driving scenario based on potential field

This paper presents 2-D pedestrian motion prediction model based on potential field for a hazard-anticipatory collision avoidance braking system to enhance the collision avoidance performance. 1-D pedestrian motion prediction reaches its limit under the situation that a pedestrian walks towards a parked vehicle as the prediction is conducted based on the current position and velocity of pedestrian within a finite time horizon. If the change of pedestrian motion can be predicted, the vehicle maneuver to avoid collision with pedestrian can be executed in advance. 2-D pedestrian motion prediction model based on potential field is constructed. The effectiveness of the proposed prediction model is verified by comparing the measured trajectory with the calculated data based on 1-D prediction and 2-D prediction.

Language

  • English

Media Info

  • Pagination: pp 39-44
  • Monograph Title: FAST-zero'15: 3rd international symposium on future active safety technology toward zero traffic accidents: September 9-11, 2015 Gothenburg, Sweden: proceedings

Subject/Index Terms

Filing Info

  • Accession Number: 01602258
  • Record Type: Publication
  • Source Agency: Swedish National Road and Transport Research Institute (VTI)
  • Files: ITRD, VTI
  • Created Date: Jun 20 2016 1:26PM