a bear? where? over there! —

Strapping a giant teddy bear to a car in the name of highway safety

Familiarity breeds awareness when it comes to advanced driver assists.

A large teddy bear is strapped to the back of an SUV as it drives on an Interstate.
Enlarge / Would you notice if a large pink bear in a high-vis vest drove past you on the highway?

Depending on your perspective, the advanced driver assistance systems (ADAS) that are appearing in more and more new cars are either a panacea for an epidemic of distracted driving or a reaction to a driving culture that doesn't take seriously enough the act of controlling thousands of pounds of high-speed machinery. It doesn't help that there's widespread public confusion, particularly when it comes to the one-two combo of adaptive cruise control and lane keeping and whether they allow a driver to nap on the freeway.

Now, a series of tests involving a large pink teddy bear, wearing a high-vis vest while strapped to the back of a moving car, has shown that using adaptive cruise and lane keeping—known in industry jargon as "SAE Level 2 automation"—can help increase a driver's situational awareness. However, the effect required some familiarity with such systems. The study was performed by the Insurance Institute of Highway Safety and published earlier this month.

You’re adapting my what?

When activated, adaptive cruise control uses forward-looking radar to maintain a specific distance to a vehicle in the lane ahead, slowing down or speeding up (to a maximum of whatever speed cruise control was set to) as necessary. Lane-keeping systems use forward-looking cameras to detect the lane markings on a road to keep the vehicle between them, and when both are active together, the vehicle will do a pretty good facsimile of driving itself, albeit with extremely limited situational awareness.

Which is where the human comes in. Under the SAE's definitions for automated driving, in Level 2 the car controls braking, acceleration, and deceleration, but the human is responsible for providing situational awareness at all times.

Of course, this raises the question of whether the driver is actually paying attention. The very newest, most advanced systems on the market use infrared cameras to track a driver's gaze to make sure they're paying attention to the road ahead, but for most ADAS-equipped cars on the road, a simple torque sensor on the steering column serves as a proxy for a real driver-monitoring system. Every so often, the car will send a tiny extra bit of torque to the steering wheel, and the torque sensor determines if the driver has their hand on the wheel. If this isn't the case, the system will begin alerting the driver and then deactivate if the driver fails to respond.

Dude, did you just see that pink bear, too?

To test whether drivers were actually paying attention while using a Level 2 system, IIHS used a variant of the "invisible gorilla test." It recruited participants and then had them drive for roughly an hour on Interstate 70 in Maryland in a 2019 Mercedes C300, either using the car's Level 2 system or not. At three predetermined locations on the test route, a second car—the one with the large pink bear attached to its trunk—would overtake the participant's vehicle. At the end of the study, the drivers were asked if they saw anything odd, and if so, how many times.

"There are a number of laboratory methods for measuring situational awareness, but they don't work so well on the road," said IIHS research scientist Alexandra Mueller, who designed the study. "The giant teddy bear on the back of the vehicle helps give us an objective measure of the driver's focus that's relevant to driving and doesn’t interfere with how that person normally drives."

The 31 participants were split into three groups. Members of the first group (n=10) had no experience using a Level 2 system, and for their hour's drive, they drove the C300 under manual control the entire time. People in the second group (n=10) were similarly inexperienced but were told to use the C300's Level 2 system for the test. The third group (n=11) did have familiarity with such systems, as its drivers owned or had regular access to a vehicle with Level 2 assists and were determined via interviews to use those assists regularly (on average, four days a week). This third group of experienced users also activated the C300's Level 2 assists for the test.

It turned out that experienced users were much more likely to notice the bear than either of the inexperienced groups. And among the inexperienced groups, those drivers who were tested while not using the Level 2 system were also more likely to notice the bear than the inexperienced group that did use the system. In fact, the inexperienced group that did use the Level 2 system were twice as likely to not spot the bear at all (compared to both the other groups). This suggests that there's a sweet spot on the learning curve between complete beginners and the superusers who have been blamed for fatal Autopilot crashes after learning how to exploit such systems.

Channel Ars Technica