Sensor-Based Control Architecture for a Car-Like Vehicle

  • Authors:

  • C. Laugier;Th. Fraichard;Ph. Garnier;I. E. Paromtchik;A. Scheuer

  • Affiliations:

  • Institut National de Recherche en Informatique et en Automatique (INRIA), Rhône-Alpes, Zirst, 655 av. de l‘Europe, 38330 Montbonnot Saint Martin, France. christian.laugier@inria ...;Institut National de Recherche en Informatique et en Automatique (INRIA), Rhˇne-Alpes, Zirst, 655 av. de l‘Europe, 38330 Montbonnot Saint Martin, France. thierry.fraichard@inri ...;Institut National de Recherche en Informatique et en Automatique (INRIA), Rhˇne-Alpes, Zirst, 655 av. de l‘Europe, 38330 Montbonnot Saint Martin, France;Institut National de Recherche en Informatique et en Automatique (INRIA), Rhˇne-Alpes, Zirst, 655 av. de l‘Europe, 38330 Montbonnot Saint Martin, France;Institut National de Recherche en Informatique et en Automatique (INRIA), Rhˇne-Alpes, Zirst, 655 av. de l‘Europe, 38330 Montbonnot Saint Martin, France

  • Venue:
  • Autonomous Robots
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a control architecture endowing a car-like vehicle movingin a dynamic and partially known environment with autonomous motioncapabilities. Like most recent control architectures for autonomous robotsystems, it combines three functional components: a set of basic real-timeskills, a reactive execution mechanism and a decision module. The mainnovelty of the architecture proposed lies in the introduction of a fourthcomponent akin to a meta-level of skills: the sensor-based manoeuvers,i.e., general templates that encode high-level expert human knowledge andheuristics about how a specific motion task is to be performed. The conceptof sensor-based manoeuvers permit to reduce the planning effort required toaddress a given motion task, thus improving the overall response-time of thesystem, while retaining the good properties of a skill-based architecture,i.e., robustness, flexibility and reactivity. The paper focuses on the trajectory planning function (which is an important part of the decisionmodule) and two types of sensor-based manoeuvers, trajectory followingand parallel parking, that have been implemented and successfully tested on a real automatic car-like vehicle placed in different situations.