Secure autonomous driving in dynamic environments: From object detection to safe driving

Secure driving in dynamic environments is an application requiring a number of premises. First of all it needs a perception system able to detect and register obstacles in the vicinity of the robot. Those obstacles are mapped and passed to a motion planner able to calculate a path considering the global objective as well as locally collision free trajectories. Finally, as the calculated path is only guaranteed to be collision free within certain boundaries, it needs a precise path following module commanding the vehicle to follow the calculated path precisely. In this paper we will show how we tackle those three primary requirements for safe driving in dynamic environments: On the perception side we use three main sensors to perceive environment information. For the mapping of arbitrary obstacles we use a setup of three different kinds of sensors. One IBEO Alasca XT Laser Scanner mounted at the front of the vehicle to provide short and long range object data, and two Sick LMS 291 looking down from the upper corners of the car securing cornering. Form those data a local traversability map is calculated that is passed to the motion planner. Another software module uses a sensor fusion approach to detect pedestrians: a laser scans analysis is computed to create weighted regions of interest in the scene ; within those regions a vision algorithm based on an advanced cascade of classifiers of fast image features is applied to precisely detect people in the perceived environment. The navigation side is using a combination of a global Field D-Star planner combined with a local path planner that forward-simulates trajectories and checks those for collisions. Finally the desired vehicle trajectory is executed by the path following algorithm using a sliding controller to keep the car on the secure track. The paper concludes with experimental results from autonomous driving in different scenarios.