Integration of planning and reactive obstacle avoidance in autonomous sensor-based navigation

This paper presents a sensor-based navigation system to safely drive vehicles in realistic scenarios. Three modules with the following functionalities compose the system: model builder, tactical planning and obstacle avoidance. These modules are integrated within a planner-reactor architecture that supervises and coordinates them in order to carry out the motion task. The emphasis of the paper is in the planning aspect and in its integration with the obstacle avoidance and modeling module. The advantage of this navigation system is to achieve a robust and trustworthy navigation in difficult scenarios, which remain troublesome for many of the existing systems. In order to validate the system, we present experiments with a wheelchair vehicle transporting a human among locations in an office type scenario.