Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, CNRS - Centre National de la Recherche Scientifique : UMR 5217, UGA - Université Grenoble Alpes
Abstract : Navigating in complex and highly dynamic environments such as crowds is still a major challenge for autonomous vehicle such as autonomous wheelchairs or even autonomous cars. This article presents a new way of navigating in crowds by using behavioral clustering for the surrounding agents and representing the crowd as a set of moving polygons. Once the environment has been modelled in this way and the robot has all the information it needs, we then propose a navigation algorithm that is able to guide the vehicle through the scene. The key-points of this algorithm are that (1) it can avoid densely-populated areas in order to minimize the risk of being on a collision course with any of the surrounding dynamic obstacles, (2) it generates socially compliant trajectories.
https://hal.inria.fr/hal-02096006
Contributor : Julie Dugdale
<>
Submitted on : Thursday, April 11, 2019 - 9:43:29 AM
Last modification on : Tuesday, September 10, 2019 - 4:13:27 PM
Roman Bresson, Jacques Saraydaryan, Julie Dugdale, Anne Spalanzani. Socially Compliant Navigation in Dense Crowds. IV 2019 - 30th IEEE Intelligent Vehicles Symposium, Jun 2019, Paris, France. pp.64-69, ⟨10.1109/IVS.2019.8814288⟩. ⟨hal-02096006⟩
