Safety Considerations in Deep Control Policies with Safety Barrier Certificates Under Uncertainty
Tom Hirshberg,Sai Vemprala,Ashish Kapoor,Tom Hirshberg,Sai Vemprala,Ashish Kapoor
Recent advances in Deep Machine Learning have shown promise in solving complex perception and control loops via methods such as reinforcement and imitation learning. However, guaranteeing safety for such learned deep policies has been a challenge due to issues such as partial observability and difficulties in characterizing the behavior of the neural networks. While a lot of emphasis in safe learn...
