Corpus ID: 211678173

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

@article{Hirshberg2020SafetyCI,
  title={Safety Considerations in Deep Control Policies with Safety Barrier Certificates Under Uncertainty},
  author={Tom Hirshberg and Sai Vemprala and Ashish Kapoor},
  journal={arXiv: Robotics},
  year={2020}
}
  • Tom Hirshberg, Sai Vemprala, Ashish Kapoor
  • Published 2020
  • Engineering, Computer Science
  • arXiv: Robotics
  • 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 learning has been placed during training, it is non-trivial to guarantee safety at deployment or test… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES

    Agile Autonomous Driving using End-to-End Deep Imitation Learning

    VIEW 1 EXCERPT

    Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing

    VIEW 1 EXCERPT

    Bridging Hamilton-Jacobi Safety Analysis and Reinforcement Learning

    VIEW 1 EXCERPT

    Constrained Policy Optimization

    VIEW 1 EXCERPT

    Control Barrier Function Based Quadratic Programs for Safety Critical Systems

    VIEW 1 EXCERPT