New Report Analyzes Human Reaction Time to Autonomous Vehicle Failures

Mineta Transportation Institute conducted a study to understand how quickly and efficiently drivers could take over vehicle control if the autonomous technology failed

Mineta Transportation Institute
A Volvo autonomous L120 wheel loader and A25F articulated hauler carry out a loading and transport operation.
A Volvo autonomous L120 wheel loader and A25F articulated hauler carry out a loading and transport operation.

Autonomous Vehicle (AV) technology is quickly expanding its market and becoming more widespread on U.S. roads. Current vehicles still require the presence of a human driver and are thus regarded as "semi-autonomous." The role of the driver is an important one, as it requires both the constant monitoring of the vehicle's operation and outside environment, as well as the capability to immediately take over control of the vehicle should a failure of the autonomous technology happen. But can a driver react in a safe and efficient manner after an autonomous technology failure scenario?

The Mineta Transportation Institute (MTI) recently published a new report, "Analysis of Disengagements in Semi-Autonomous Vehicles: Drivers’ Takeover Performance and Operational Implications" that explores the answer to such a question.

The study placed human drivers in a high-fidelity integrated car simulator capable of handling both human and autonomous driving. A population of 40 individuals was tested to understand how quickly and efficiently drivers could takeover vehicle control if the autonomous technology (AT) failed. “In the safety-critical situation of an AT disengagement, it is important to ensure that the human driver has enough time to react and respond effectively to the vehicle’s request for human control,” says Dr. Francesca Favaro, the project’s Principal Investigator in a short video interview about her collaboration with MTI.

“We tested control takeover metrics including response times and vehicle drift from centerline under several different scenarios,” notes Favaro. “Despite a small sample size, our results have important operational implications.”

Key results included:

  • Of the two speed settings selected for the study (high speed of 65 mph and low speed of 55 mph), the low-speed category yielded better performance for all test subjects.
  • Three age groups were tested (18-34 years, 35-54 years, and 55+ years) and the older drivers performed best in terms of both maximum drift and comparison between conventional manual driving and driving after AT failure.
  • More than three-quarters of drivers resorted to acceleration and steering rather than braking and decreasing the vehicle’s speed after they took over the vehicle control, and one-third of those actually thought they had braked instead of accelerating when asked to recall their reaction to the disengagement.
  • All participants received both an auditory and visual warning for the disengagement, but half of them reported not seeing the visual warning on the central console.

From a regulatory standpoint, the preliminary results point to the importance of setting thresholds for maximum operational speed of vehicles driven in autonomous mode when the human driver serves as back-up, perhaps warranting a lower speed limit than conventional vehicles. This research shows that the establishment of an operational threshold could reduce the maximum drift and lead to better control during takeover. Unintentional drift also attests to the need for discussions on possible dedicated lane usage for autonomous vehicles and separation from conventional traffic, as well as for the possibility of increasing lane width in dedicated lanes for semi-autonomous vehicles. With regard to the age variable, neither the response times analysis nor the drift analysis provide support for any claim to limit the age of drivers of semi-autonomous vehicles.

Discover more:

Autonomous Construction Equipment is Coming, but “Assist” is Here Now

Caterpillar Autonomous Haul Trucks Point To Construction’s Future

[VIDEO] Built Robotics Develops Autonomous Track Loader for Construction

Is the Future of Transportation Autonomous?

Bobcat Partners with SafeAI to Bring Autonomous Machines to Construction

Mortenson to Deploy Autonomous Equipment on Remote Worksites

Sunstate Partners with Built Robotics to Rent Autonomous Earthmovers