Control and perception components for autonomous vehicle guidance. Application to the ROMEO vehicles

摘要

This paper presents several control and perception components that implement navigation behaviours in autonomous vehicles. A behaviour-based control architecture integrating these components is also presented. The paper concentrates on autonomous tracing behaviours. In particular, the tracing of explicit paths, moving targets and environmental features are described. These behaviour have been implemented using several different position estimation techniques: dead reckoning; global position estimation using GPS; and position estimation with respect to the environment. The control architecture has been implemented in ROMEO vehicles at the University of Seville. These autonomous vehicles are adaptated from conventional electric vehicles and are currently used for experiments in autonomous navigation and teleoperation in outdoor environments. A short description of the general characteristics of the ROMEO-3R (tricycle) and ROMEO-4R (four wheels) vehicles is presented. The paper includes results from the tracing of environmental features with proximity sensors, and visual tracing of moving targets.