Researchers at North Carolina State University announced on Mar. 11 a new approach to the remote operation of so-called “driverless” cars, aiming to address challenges faced by human operators who control these vehicles from a distance.
The topic is important as the use of remotely operated autonomous vehicles grows, raising questions about safety, operator workload, and regulatory oversight. Ensuring that remote operators remain alert and are not overwhelmed is seen as critical for preventing accidents and improving transportation safety.
Jing Feng, professor of human factors psychology at NC State, said that while some autonomous vehicles have remote human operators who assist in complex scenarios, there are significant challenges. “There are automobiles that are largely autonomous but that actually have remote human operators who provide guidance or assistance when a vehicle encounters a complex scenario,” Feng said. “The goal here is to ensure that the vehicle navigates the situation successfully, mitigating any risk of harm to passengers, other vehicles, and so on. Recent news stories suggest that Waymo taxis are an example of this.”
Feng outlined three main issues: maintaining vigilance among operators during periods of low activity; managing cognitive workload so operators do not monitor more vehicles than they can handle; and ensuring timely intervention in dynamic environments such as city streets or highways. “For example, research shows that remote operators can monitor two vehicles very well, but their performance declines significantly when asked to monitor four vehicles – it’s simply too mentally taxing,” Feng said.
Current systems typically rely on reactive approaches where operators intervene only after receiving prompts from the vehicle’s autonomous system. The researchers propose a proactive approach instead. “This would give remote operators more system information, and would also require closer monitoring, but would allow operators to better anticipate problems,” Feng said. She added that this could lead to faster response times and fewer mistakes.
The team plans further research with support from the North Carolina Department of Transportation to explore policy and regulatory implications for robotaxi operations. Their findings appear in a chapter titled “Proactive Remote Operation of Automated Vehicles: Supporting Human Controllability” in the Handbook of Human-Centered Artificial Intelligence.
