Scroll to top

Researchers highlight the need to address remote control of self-driving cars by human operators

2021-02-19 13:56:06
{widget1}

Credit: Royal Holloway, University of London

A new article published by Royal Holloway and TRL highlights that the self-driving vehicles of the future will occasionally require remote human intervention in the event that the vehicle's technology fails. According to current industry figures, an automated vehicle may require remote human assistance approximately every 13,000 miles.

The researchers are calling on the autonomous vehicle industry to update current knowledge of automated driving to take on the role of a human operator from a remote location. The remote operator can provide assistance to passengers on board or remotely manage the situation for the vehicle and determine the next action. In more extreme cases, they may need to take over full remote control and drive the vehicle to a safer location. Crucially, industry standard regulations and safety protocols must be put in place regarding the training required for remote operation and the equipment and technology essential to the role.

There are significant differences between being aware of your surroundings in a normal driving environment and temporarily operating a vehicle from a remote location. As the UK begins to shift to an ever-increasing level of vehicle autonomy, the article highlights the urgent need to investigate the unique challenges remote operators will face when trying to become aware of the environment around a vehicle that they do not physically occupy.

The article, published in Cognitive Inquiry: Principles and Implications, argues that in remote environments it can be beneficial to make a remote driver's driving experience as realistic as possible, using technology such as Augmented Reality and Virtual Reality to enhance their sense of in-vehicle embodiment.

Clare Mutzenich, an ESRC-funded Ph.D. Researcher from Royal Holloway's psychology department said: “If a problem arises in an automated vehicle that prevents it from navigating independently to its destination, a remote human operator may need to intervene.

“We argued that the understanding of vehicle automation in the industry should be expanded to include the role of the external operator, who would intervene from another location.

"Our study is examining what level of consciousness is sufficient to safely drive a vehicle remotely, how long it takes to build this level of awareness, and whether situational awareness would be improved by providing additional information."

Dr. Shaun Helman, Chief Scientist at TRL and co-supervisor for the Ph.D., said, “Work at TRL has clearly shown that the promise of automated vehicles will only be realized if we have a holistic understanding of the system. the answer, and this project fills an important gap in our current understanding – that of the needs of remote operators. "

Camilla Fowler, Head of Automation at TRL added: “At TRL, we explore the implications for remote operation from a safety assurance perspective and discuss the liability issues associated with it, so this research into the load on an external operator is an essential part of the puzzle. . "


COVID-19 has fueled automation, but human engagement is still essential


More information:
Updating our understanding of situational awareness related to remote drivers of autonomous vehicles. Cogn. Research 6, 9 (2021). doi.org/10.1186/s41235-021-00271-8

Supplied by
Royal Holloway, University of London

QuoteResearchers stress the need to address the remote control of self-driving cars by human operators (2021, February 19)
Retrieved February 19, 2021
from https://techxplore.com/news/2021-02-highlight-remote-self-driving-cars-human.html

This document is protected by copyright. Aside from any fair treatment for the purposes of private study or research, no
some may be reproduced without written permission. The content is provided for informational purposes only.

{widget2}

Post a comment

Your email address will not be published. Required fields are marked *