MIT study finds Tesla drivers become inattentive when Autopilot is activated – TechCrunch

By the end of this week, thousands of Tesla owners may be testing the automaker’s latest version of its “Full Self-Driving” beta software, version 10.0.1, on public roads, even as regulators and federal officials monitor the safety of the system. after a few high-profile crashes.

a new study from the Massachusetts Institute of Technology gives credence to the idea that the FSD system, which despite its name isn’t actually an autonomous system, but rather an Advanced Driver Assistance System (ADAS), may not be as safe. Researchers studying data from 290 human-initiated Autopilot disconnection periods found that drivers can become inattentive when using partially automated driving systems.

“Visual behavioral patterns change before and after [Autopilot] exit,” the investigation reads. “Before the shutdown, drivers looked less at the road and concentrated more on non-driving areas compared to after the switch to manual driving. The larger share of off-road looks before switching to manual driving was not compensated by longer looks ahead.”

Tesla CEO Elon Musk has said that not everyone who has paid for the FSD software will have access to the beta version, which promises more automated driving features. First, Tesla will use telemetry data to record personal driving stats over a seven-day period to ensure drivers still remain vigilant. The data could also be used to implement a new safety review page that tracks the owner’s vehicle, which is linked to their insurance.

The MIT study provides evidence that drivers may not be using Tesla’s Autopilot (AP) as recommended. Because AP includes safety features such as traffic-aware cruise control and automatic steering, drivers become less attentive and take their hands off the wheel more. The researchers found that this kind of behavior may be the result of a misunderstanding of what the AP functions can do and what the limitations are, which is reinforced when it performs well. Drivers whose tasks are automated for them may naturally become bored after attempting to maintain visual and physical alertness, which only leads to increased inattention, researchers say.

The report, titled “A Model of Naturalistic Gaze Around Tesla Autopilot Disabling,” follows Tesla Model S and X owners in the Boston area over a period of a year or more as they go about their daily routine. The vehicles were equipped with the Real-time Intelligent Driving Environment Recording data acquisition system1, which continuously collects data from the CAN bus, a GPS and three 720p video cameras. These sensors provide information such as vehicle kinematics, driver interaction with the vehicle controllers, mileage, location and driver position, face and view in front of the vehicle. MIT collected nearly 500,000 miles of data.

The purpose of this study is not to put Tesla to shame, but to advocate for driver attention management systems that can provide drivers with real-time feedback or tailor automation functionality to a driver’s level of attention. Currently, Autopilot uses a hands-on-wheel detection system to monitor driver involvement, but it does not monitor driver attention through eye or head tracking.

The researchers behind the study have developed a gaze behavior model, “based on naturalistic data, that can help understand the characteristics of driver attention shifts under automation and support the development of solutions to ensure that drivers are sufficiently engaged.” stick to driving tasks.” Not only would this help driver monitoring systems address “atypical” looks, but it could also be used as a benchmark to study the safety effects of automation on a driver’s behavior.

Companies such as Seeing Machines and Smart Eye are already working with automakers such as General Motors, Mercedes-Benz and reportedly Ford to bring camera-based driver tracking systems to ADAS-equipped cars, as well as address problems caused by driving under the influence or driving under the influence. The technology exists. The question is, will Tesla use it?