A self-adaptive agent-based path following control lateral regulation and obstacles avoidance

Since a couple of years, transportation systems have been entering into mutation. The part of the autonomous abilities of vehicles increases significantly with their associate constraints and problematic. Among these abilities, trajectory following is one of the minimum competence required for vehicles or mobile robots autonomy. Generally, the computation of the path to follow is made “off-line” and then is transmitted to the vehicle. The main problem then encountered is the fact that the model of the evolution area of the vehicle may have changed between the computation of the plan and its execution. If unpredictible events occur during the vehicle moves, one must recompute a local plan taking into account these new events and respecting as far as it is possible the initial plan. Since the computation of the plan for a trajectory is costly and since the computation power of a vehicle is limited, it is hardly possible to embed this kind of ability directly into vehicles. This paper proposes a reactive multi-agent based solution to address this problem with low computation power requirement and adaptive abilities allowing obstacle avoidance.