Skip to Main content Skip to Navigation
Conference papers

Proactive Longitudinal Velocity Control In Pedestrians-Vehicle Interaction Scenarios

Maria Kabtoul 1 Philippe Martinet 1 Anne Spalanzani 2
2 CHROMA - Robots coopératifs et adaptés à la présence humaine en environnements dynamiques
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
Abstract : Navigation in pedestrian populated environments is a highly challenging task, and a milestone on the way to fully autonomous urban driving systems. Pedestrian populated environments are highly dynamic, uncertain and difficult to predict. The strict safety measures in such environments result in overly reactive navigation systems, which do not match the conduct of experienced drivers. An autonomous vehicle driving alongside pedestrians should convey a natural and a socially-aware behaviour. Therefore, the vehicle should not merely react to the behaviour of the surrounding agents, but should rather cooperate and proactively interact with its surrounding. Excluding this aspect from the navigation scheme results in over-reactive behaviours, an unnatural driving pattern and a suboptimal navigation solution. This paper presents a proactive longitudinal velocity control method, appropriate for navigation in close interaction with pedestrians. The work uses a cooperation-based pedestrians-vehicle behavioural model to find the optimal longitudinal velocity control. The method is implemented in lateral crossing scenarios with a dense crowd of pedestrians. The results are then compared with a reactive navigation system. The method is evaluated in terms of the vehicle's travel time and the safety of the pedestrians in the scene.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.inria.fr/hal-02944369
Contributor : Maria Kabtoul <>
Submitted on : Monday, September 21, 2020 - 2:09:24 PM
Last modification on : Wednesday, October 7, 2020 - 3:34:24 AM

File

ITSC20_Kabtoul_Martinet_Spalan...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02944369, version 1

Citation

Maria Kabtoul, Philippe Martinet, Anne Spalanzani. Proactive Longitudinal Velocity Control In Pedestrians-Vehicle Interaction Scenarios. The 23rd IEEE International Conference on Intelligent Transportation Systems, Sep 2020, Rhodes, Greece. ⟨hal-02944369⟩

Share

Metrics

Record views

45

Files downloads

100