Predictive Display with Perspective Projection of Surroundings in Vehicle Teleoperation to Account Time-delays

TL;DR

This paper introduces a perspective projection method combined with Smith predictor correction to forecast future vehicle views in teleoperation, effectively mitigating variable network delays and improving control accuracy.

Contribution

It presents a novel approach integrating perspective projection with Smith predictor to forecast vehicle views, addressing variable delays in teleoperation.

Findings

Reduced path deviation in street edge maneuvers

Effective compensation for network delay variability

Improved teleoperation control accuracy

Abstract

Teleoperation provides human operator sophisticated perceptual and cognitive skills into an over the network control loop. It gives hope of addressing some challenges related to vehicular autonomy which is based on artificial intelligence by providing a backup plan. Variable network time delays in data transmission is the major problem in teleoperating a vehicle. On 4G network, variability of these delays is high. Due to this, both video streaming and driving commands encounter variable time delay. This paper presents an approach of providing the human operator a forecast video stream which replicates future perspective of vehicle field of view accounting the delay present in the network. Regarding the image transformation, perspective projection technique is combined with correction given by smith predictor in the control loop. This image transformation accounts current time delay and tries to address both issues, time delays as well as its variability. For experiment sake, only frontward field of view is forecast. Performance is evaluated by performing online vehicle teleoperation on street edge case maneuvers and later comparing the path deviation with and without perspective projection.