Timezone: »

Infrastructure-based End-to-End Learning and Prevention of Driver Failure
Noam Buckman · Shiva Sreeram · Mathias Lechner · Yutong Ban · Ramin Hasani · Sertac Karaman · Daniela Rus

Intelligent intersection managers can improve safety by detecting dangerous drivers or failure modes in autonomous vehicles, warning oncoming vehicles as they approach an intersection. In this work, we present FailureNet, a recurrent neural network trained end-to-end on trajectories of both nominal and reckless drivers in a scaled miniature city. FailureNet observes the poses of vehicles as they approach an intersection and detects whether a failure is present in the autonomy stack, warning cross-traffic of potentially dangerous drivers. FailureNet can accurately identify control failures, upstream perception errors, and speeding drivers, distinguishing them from nominal driving. The network is trained and deployed with autonomous vehicles in a scaled miniature city. Compared to speed or frequency-based predictors, FailureNet's recurrent neural network structure provides improved predictive power, yielding upwards of 84% accuracy when deployed on hardware.

Author Information

Noam Buckman (MIT CSAIL)
Noam Buckman

Noam Buckman is a PhD Candidate in the Distributed Robotics Lab at the Massachusetts Institute of Technology. His research interests include socially-aware planning, game theory, multi-robot coordination, and robot platforms. Noam received his B.S. in Mechanical Engineering and Mathematics and M.S. in Mechanical Engineering from MIT.

Shiva Sreeram (Caltech)
Mathias Lechner (MIT)
Yutong Ban (MIT)
Ramin Hasani (MIT | Vanguard)
Sertac Karaman (MIT)
Daniela Rus (Massachusetts Institute of Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors