Camera and Radar-based Perception System for Truck Platooning

Abstract

Truck platooning is a driving method with multiple trucks maintaining a very close gap between them, e.g., under 10 m at 90 km/h. The close longitudinal distance imposes a challenge for its perception system since a major portion of the front direction is occluded by the trailer in front. With this challenge, we present a radar and camera-based perception system for truck platooning. First, to improve the lane detection accuracy even with the serious occlusion problem, the distance to the front vehicle obtained by a radar is exploited to set a precise region of interest (ROI). Second, a state-of-the-art camera-based object detector is employed with our vehicle tracking mechanism. Third, the vehicle tracking information from the radar is fused to provide more reliable longitudinal information which is not available in the camera. Above methods are actually implemented in an embedded computer and evaluated in a highway driving scenario with prototype trucks.