Retaking wheel of self-driving cars ‘especially risky’ — study

Vast sums of money are being propelled into the vision of self-driving cars by both venture capital firms and global corporations, including the likes of Intel, BMW and Apple. And the race is on to be the first to launch an autonomous vehicle.

Hit the brakes, say researchers at Stanford University and Ben-Gurion University of the Negev. The transition that occurs when a driver retakes control of a vehicle “could be rough,” the researchers warn, based on the results of a study, noting that their findings could help in the design of future autonomous cars.

As part of the research, 22 drivers were asked to put that question to a test — on a track, not a freeway. The researchers, who had a combined expertise in autonomous car design, human-robot interaction research and neuroscience, found drivers who experienced certain changes in driving conditions since their last time at the wheel, such as changes in speed, had a period of adjustment in their steering. The results were published in the first issue of Science Robotics on December 6.

“We need to acknowledge that people’s performance might not be at its peak if they haven’t actively been participating in the driving,” Holly Russell, lead author of the research and former graduate student in the Dynamic Design Lab at Stanford University.

After taking back control of the wheel, drivers had trouble getting used to different driving conditions. The trouble wasn’t enough to cause them to miss their turns, but it was noticeable in the researchers’ measurements and by watching them manipulate the wheel to account for over- and understeering. So, depending on the driver, the driving conditions and the autonomous system being used, the researchers warn that these challenges raise a possibility that the transition back to driver-controlled driving could be “an especially risky window of time.”

Study participants drove a 15-second course consisting of a straightaway and a lane change. Then they took their hands off the wheel and the car took over, bringing them back to the start. After going through this process four times, they drove the course 10 additional times with steering conditions that were modified to represent changes in speed or steering that may occur while the car drives itself.

Even knowing about changes in speed and steering, being able to make a plan and do some explicit motor planning for how to compensate, “you still saw a very different steering behavior and compromised performance,” said Lene Harbott, co-author of the research and research associate in the Revs Program at Stanford.

“In neuroscience this is explained as a difference between explicit and implicit learning,” said IIana Nisky, co-author of the study and senior lecturer at Ben-Gurion University of the Negev in Israel. “Even when a person is aware of a change, their implicit motor control is unaware of what that change means and can only figure out how to react through experience.”

Although these drivers were not so thrown off by the changes in steering that they drove off-course, the fact that there is a period of altered steering behavior is still significant, the researchers said. There are so many different variables involved in driving that anything that compromises driving performance could lead to an accident, they said.

In the research, the test vehicle driven was developed at Stanford and doesn’t represent any system currently available, they said. The study addressed one specific example of handover, but there is still a lot to learn about how people respond in other circumstances, depending on the type of car, the driver and how the driving conditions have changed, the researchers said.

“If someone is designing a method for automated vehicle handover, there will need to be detailed research on that specific method,” said Harbott. “This study is the tip of the iceberg.”

Apple, Audi, China’s search giant Baidu and a consortium of BMW with Intel and Mobileye are among the corporate groups that are involved in the development of advanced driver assistance systems and self-driving vehicles. Private companies working in the auto tech sector are set to attract a record level of deals and funding this year, New York-based data company CB Insights said in a report, with autonomous driving startups leading the list. Investments in 2016 in deals for auto tech startups are on track to reach an estimated record $847 million, well above the $478 million in financing the sector received in the whole of 2015, the data company said.