Pedestrian Occupancy Prediction for Autonomous Vehicles

Peter Zechel, Ralph Streiter, Klaus Bogenberger, Ulrich Gohner

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

This paper presents a new approach to determining the occupancy area of a pedestrian for autonomous driving. To do this, a probabilistic prediction of pedestrian behavior is calculated, which results in the probability of presences. The occupancy prediction can be determined on the basis of this probability as a function of an accepted risk. To predict the behavior, the first step involves using a physical model to determine the possible presence locations. The subsequent assessment of the movement options based on the statistically representative pedestrian behavior, the relevant static objects and the interaction of dynamic objects allows the probabilities of presences to be determined in arbitrary situations. The effectiveness of the prediction is illustrated by using a numerical example which indicates the reduction of occupancy area size by using a suitable prediction method.

Original languageEnglish
Title of host publicationProceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages230-235
Number of pages6
ISBN (Electronic)9781538692455
DOIs
StatePublished - 26 Mar 2019
Externally publishedYes
Event3rd IEEE International Conference on Robotic Computing, IRC 2019 - Naples, Italy
Duration: 25 Feb 201927 Feb 2019

Publication series

NameProceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019

Conference

Conference3rd IEEE International Conference on Robotic Computing, IRC 2019
Country/TerritoryItaly
CityNaples
Period25/02/1927/02/19

Keywords

  • autonomous cars
  • interaction-aware
  • motion prediction
  • occupancy prediction

Fingerprint

Dive into the research topics of 'Pedestrian Occupancy Prediction for Autonomous Vehicles'. Together they form a unique fingerprint.

Cite this