Ashish Kapoor

Verifying Controllers Against Adversarial Examples with Bayesian Optimization

2018

Recent successes in reinforcement learning have lead to the development of complex controllers for realworld robots. As these robots are deployed in safety-critical applications and interact with humans, it becomes critical to ensure safety in …

Safety Considerations in Deep Control Policies with Safety Barrier Certificates Under Uncertainty

2020

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 …