Skip to Main content Skip to Navigation
Conference papers

Motion Planning and Sensor-Guided Manoeuvre Generation for an Autonomous Vehicle

Christian Laugier 1 Philippe Garnier 1 Thierry Fraichard 1 Igor Paromtchik 1 Alexis Scheuer 1
1 SHARP - Automatic Programming and Decisional Systems in Robotics
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes
Abstract : This paper deals with a novel motion control approach for a car-like vehicle evolving in a dynamic and partially known environment. After having briefly presented the overall architecture of the control system and the related Global Trajectory Planner, we will put the emphasis onto the Manoeuver Execution module and its inter-connections with the off-line and the on-line motion planning functions. The key idea of the approach is to plan and carry out sensor-guided manoeuvres: first, a nominal trajectory is generated using a reconstructed model of the world and a prediction of the most likely behaviors of the moving entities; then, the involved motion controls are generated and executed using a reactive scheme for taking into account the unforeseen events. This is done using local trajectories associated with some generic sensor-based manoeuvres. Such trajectories are planned on-line and immediately executed by the system. Experimental results obtained with our automatic car-like vehicle are presented for two types of manoeuvres: lane following/changing and autonomous parallel parking.
Complete list of metadatas

https://hal.inria.fr/inria-00000016
Contributor : Alexis Scheuer <>
Submitted on : Tuesday, May 10, 2005 - 4:15:49 PM
Last modification on : Friday, June 26, 2020 - 4:04:02 PM

Identifiers

  • HAL Id : inria-00000016, version 1

Collections

Citation

Christian Laugier, Philippe Garnier, Thierry Fraichard, Igor Paromtchik, Alexis Scheuer. Motion Planning and Sensor-Guided Manoeuvre Generation for an Autonomous Vehicle. Int. Conf. on Field and Service Robotics, Dec 1997, Canberra (AU), Australia. pp.56-65. ⟨inria-00000016⟩

Share

Metrics

Record views

429