Sensor Augmented Virtual Reality Based Teleoperation Using Mixed Autonomy

摘要

A multimodal teleoperation interface is introduced, featuring an integrated virtual reality (VR) based simulation augmented by sensors and image processing capabilities onboard the remotely operated vehicle. The proposed virtual reality interface fuses an existing VR model with live video feed and prediction states, thereby creating a multimodal control interface. VR addresses the typical limitations of video based teleoperation caused by signal lag and limited field of view, allowing the operator to navigate in a continuous fashion. The vehicle incorporates an onboard computer and a stereo vision system to facilitate obstacle detection. A vehicle adaptation system with a priori risk maps and a real-state tracking system enable temporary autonomous operation of the vehicle for local navigation around obstacles and automatic re-establishment of the vehicle’s teleoperated state. The system provides real time update of the virtual environment based on anomalies encountered by the vehicle. The VR based multimodal teleoperation interface is expected to be more adaptable and intuitive when compared with other interfaces.