The use of Obstacle Motion Tracking for Car-like Mobile Robots Collision Avoidance in Dynamic Urban Environments

One of the most challenging tasks for mobile robots is to track mobile obstacles that surround them. This task is especially difficult in outdoor environments where a great variety of obstacles may induce the robot to take erroneous decisions. The mobile robot needs as much information as possible concerning the obstacle positions and speeds (direction and magnitude) in order to plan evasive maneuvers that avoid collisions. Unfortunately, obstacles close to robot’s sensors frequently cause blind zones behind them where other obstacles could be hidden. In this situation, the robot may lose vital information about these obstructed obstacles that could avoid future collisions. In order to overcome this problem an obstacle tracking module based only on 2D laser scan data was developed. Its main parts consist of obstacle detection, obstacle classification, and obstacle tracking. Different methods were evaluated for extracting data from the laser data. Geometrical feature extraction itself, i.e. lines and corners, was not found sufficient. Therefore, a motion detection module using scan matching was developed. The research was mostly conducted using a MatLab simulator that reproduces a simple 2D urban-like environment with parked and moving cars, buses, trucks, and people, buildings, streets, and trees. Aiming to adjust and validate the algorithms, some samplings of real data were carried out. The tests proved the applicability of the algorithms in real urban environments and in a near future they will be used in obstacle avoidance procedures onboard a real car-like robot.