Synthesized Scene Recollection for Vehicle Teleoperation

Abstract

In this paper we propose an innovative view synthesis method for vehicle teleoperation, a synthesized scene recollection method, which provides the operator with a bird's-eye view image of the vehicle in an environment which is generated by using position and orientation information of the vehicle, stored image history data captured by a camera mounted on the vehicle, and the CG model of the vehicle. This method helps the operator to easily recognize the situation of the vehicle even in unknown surroundings and enables the remote operation ability of a vehicle to be improved. We also propose the different ways of presenting the synthesized bird's-eye view images to an operator. This method is mainly based on two technologies, vehicle positioning and image synthesis. To realize self-contained system of the proposed method we use scan matching of the scan data of a laser rangefinder for vehicle positioning. Experimental results for a robot in 2D horizontal plane are shown.