A Control Lyapunov Perspective on Episodic Learning via Projection to State Stability

@article{Taylor2019ACL,
  title={A Control Lyapunov Perspective on Episodic Learning via Projection to State Stability},
  author={Andrew J. Taylor and Victor D. Dorobantu and Meera Krishnamoorthy and Hoang Minh Le and Yisong Yue and Aaron D. Ames},
  journal={2019 IEEE 58th Conference on Decision and Control (CDC)},
  year={2019},
  pages={1448-1455}
}
  • Andrew J. Taylor, Victor D. Dorobantu, +3 authors Aaron D. Ames
  • Published in
    IEEE 58th Conference on…
    2019
  • Computer Science, Mathematics
  • The goal of this paper is to understand the impact of learning on control synthesis from a Lyapunov function perspective. In particular, rather than consider uncertainties in the full system dynamics, we employ Control Lyapunov Functions (CLFs) as low-dimensional projections. To understand and characterize the uncertainty that these projected dynamics introduce in the system, we introduce a new notion: Projection to State Stability (PSS). PSS can be viewed as a variant of Input to State… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-4 OF 4 CITATIONS

    Learning for Safety-Critical Control with Control Barrier Functions

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS

    Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems*

    VIEW 1 EXCERPT

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES

    Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems*

    VIEW 8 EXCERPTS

    Smooth stabilization implies coprime factorization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Stabilization with relaxed controls

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural Lander: Stable Drone Landing Control Using Learned Dynamics

    VIEW 1 EXCERPT