This paper presents a control architecture endowing a car-like vehicle movi
ng in a dynamic and partially known environment with autonomous motion capa
bilities. Like most recent control architectures for autonomous robot syste
ms, it combines three functional components: a set of basic real-time skill
s, a reactive execution mechanism and a decision module. The main novelty o
f the architecture proposed lies in the introduction of a fourth component
akin to a meta-level of skills: the sensor-based manoeuvers, i.e., general
templates that encode high-level expert human knowledge and heuristics abou
t how a specific motion task is to be performed. The concept of sensor-base
d manoeuvers permit to reduce the planning effort required to address a giv
en motion task, thus improving the overall response-time of the system, whi
le retaining the good properties of a skill-based architecture, i.e., robus
tness, flexibility and reactivity. The paper focuses on the trajectory plan
ning function (which is an important part of the decision module) and two t
ypes of sensor-based manoeuvers, trajectory following and parallel parking,
that have been implemented and successfully tested on a real automatic car
-like vehicle placed in different situations.