Perception Systems: Sense and Understanding
2getthere is actively developing enhanced perception systems for better sense and understanding. This includes sensor fusion, using 3D camera systems, LiDAR, radar and ultrasound sensors as well as classification. The aims are to improve redundancy and safety, ensure operations under all adverse weather conditions and ultimately 360-degree awareness. The latter is especially for operations in mixed traffic with other road users, allowing to anticipate the unexpected through recognition and understanding of their intentions.
Original use: obstacle detection
Even in the 1997 Schiphol and the 1999 Rivium application, the vehicles were already equipped with LiDAR sensors for obstacle detection. A failsafe detection algorithm is used that scans the area in front of the vehicles ‘empty’, capable to detect obstacles of 7+ centimeters wide within a reach of 40-100 meters. It is able to distinguish true obstacles from ‘ghost’ objects such as rain, snow or leaves falling from the trees, plugging in to the low level motion controllers to interrupt the navigation task when required.
The software for the interpretation of the sensor raw scans is developed in-house. By combining the data from the sensors with the planned path, the vehicles can react to objects in their path (base hull) as adjancent to it (extended hull). Both hulls are divided into cells, each scanned several times per second to determine the type of object, the direction it is moving in and at what speed. Based on the information the appropriate reaction for the vehicle is determined.