Predictive haptic feedback for safe lateral control of teleoperated road vehicles in Urban Areas

Lateral control of teleoperated vehicles is a significant challenge for human operators while driving within dense urban scenarios. This paper presents the general system design of a novel haptic assistance system for safe lateral control of these vehicles. The proposed system is based on a direct control structure to keep the human operator as the main decision maker in human- machine cooperating steering tasks. The haptic system uses a two-stage prediction on a LiDAR occupancy grid. The first prediction stage compensates the communication time delay with which the actual states of the teleoperated vehicle as well as other dynamic objects in the environment are predicted. For the second prediction stage, an extension of the look-ahead approach is proposed, which predicts side collisions and generates a smooth haptic feedback at the steering wheel of the operator workstation. The resulted haptic assistance system supports the human operator in a generic way at all challenging scenarios without the need for road information. The results of the test drives conducted by experienced operators show the capability of the developed system to assist the human operator at preventing side collisions as well as stabilizing the lateral control of teleoperated vehicles.