Chris Gerdes
Stanford University | Professor of Mechanical Engineering
TALK DESCRIPTION
Automated vehicles provide an unparalleled opportunity to reduce the approximately 35,000 fatalities that occur each year on US roads. With the ability to sense 360 degrees around the vehicle, avoid distraction and react within milliseconds, automated vehicles possess some inherent advantages over human drivers when it comes to avoiding collisions. To realize this potential, however, the cars must be explicitly designed to make full use of these advantages when designing and executing maneuvers.
For inspiration, we have been studying race car drivers, who are able to routinely handle cars safely at the very limits of their handling capabilities. By working with expert drivers and measuring their performance on the track, we have developed automated vehicles capable of lapping a track in less time than a champion amateur driver and drifting through courses with a precision exceeding human capability. More importantly, we are developing entirely new approaches to controlling cars that can transfer from race track performance to highway safety.
Even with driving capability at the level of the best human drivers, not all collisions are avoidable, due to laws of physics and the somewhat unpredictable actions of human road-users. Automated vehicles must be explicitly designed for these cases as well, requiring engineers to consider not only technical feasibility but also ethical frameworks for decision-making. Just as we sought out race car drivers to teach us about handling the car, we are now working with philosophers to handle these more human aspects of automation.