Skip to Main content Skip to Navigation
Conference papers

Vehicle control using image cues recognition

Abstract : Since several years, researchers attempt to design algorithms able to control a vehicle by using computer vision. Several approaches are now available but more often the vehicle control is achieved in separate way from the perception task. Indeed the vehicle state is combined with perception parameters to feed the regulation task. This paper presents the reliability of an original approach which combines perception and control task. The system we have designed is able to recognize roadsides from images cues in different situations (highway, road, etc), and to compute the vehicle wheel angle and several location parameters too. In particular, we present the need for achieving a training stage (given either by a control law or by a experimented human driver) to provide a good control law. The algorithm behavior is then presented in simulated and real situations as well in order to prove the reliability of the approach on an agricultural vehicle.
Document type :
Conference papers
Complete list of metadata
Contributor : Migration Irstea Publications Connect in order to contact the contributor
Submitted on : Thursday, May 14, 2020 - 8:44:12 PM
Last modification on : Wednesday, September 28, 2022 - 3:07:12 PM


  • HAL Id : hal-02580896, version 1
  • IRSTEA : PUB00010877



J. Laneurit, Romain Chapuis, Christian Cariou, R. Aufrere. Vehicle control using image cues recognition. 12th International Symposium on Measurement and Control in Robotics (ISMCR 2002), ENSIB de Bourges, 20-22 June 2002, 2002, France. pp.4. ⟨hal-02580896⟩



Record views