Cars that coordinate with people

Autonomous cars tend to treat people like obstacles whose motion needs to be anticipated so that the car can best stay out of their way, resulting in ultradefensive cars that can't coordinate with people. Anca Dragan demonstrates how learning and optimal control can be leveraged to generate car behavior that results in natural coordination strategies.

Autonomous cars tend to treat people like obstacles whose motion needs to be anticipated so that the car can best stay out of their way, resulting in ultradefensive cars that can’t coordinate with people. They miss a key aspect of coordination: it’s not just the car interpreting and responding to the actions of people; people also interpret and respond to the car’s actions. Anca Dragan introduces a mathematical formulation of interaction that accounts for this and demonstrates how learning and optimal control can be leveraged to generate car behavior that results in natural coordination strategies, such as the car negotiating a merge or inching forward at an intersection to test whether it can go.