Tesla makes the foremost popular electric vehicles on the market today. Many of Tesla’s vehicles are equipped with its Autopilot driver assistance system, allowing vehicles to drive themselves in some situations. However, Autopilot doesn’t make Tesla’s automobiles fully autonomous, and therefore the system requires driver attention.
Unfortunately, several high-profile crashes leading to fatalities are imagined to have occurred while Autopilot was engaged. A replacement study conducted by MIT is investigated what it terms non-critical disengagement of Tesla’s Autopilot in naturalistic highway driving. The study began to work out if drivers are getting inattentive while using partially automated driving systems.
The main premise of the study is that the security impact of inattention behind the wheel with systems like Autopilot is unknown until we’ve data on how visual behaviour is modified with automation. The study investigated data from 290 human-initiated Autopilot disengagements. Additionally, study researchers investigated glance duration and transition using Bayesian Generalized Linear Mixed Models.
In the study, the model replicated observed glance patterns across a variety of drivers. Researchers found that off-road glances were longer with Autopilot active than when it had been when inactive. The team also found that the frequency of off-road glances specifically associated with driving was less frequent with Autopilot active than while manually driving.
During driving, non-driving-related glances down or to the middle stack areas were the foremost frequent and longest, with 22 per cent of these glances exceeding two seconds. The study found little difference in on-road glance duration. The study concluded that visual behaviour patterns change before and after Autopilot is employed. Before Autopilot was disengaged, drivers within the study checked out the road less and focused more on areas unrelated to the driving task than once they were driving manually.