Safe Control of Partially-Observed Linear Time-Varying Systems with Minimal Worst-Case Dynamic Regret
We present safe control of partially-observed linear time-varying systems in the presence of unknown and unpredictable process and measurement noise. We introduce a control algorithm that minimizes dynamic regret, i.e., that minimizes the suboptimality against an optimal clairvoyant controller that knows the unpredictable future a priori. Specifically, our algorithm minimizes the worst-case dynamic regret among all possible noise realizations given a worst-case total noise magnitude. To this end, the control algorithm accounts for three key challenges: safety constraints; partially-observed time-varying systems; and unpredictable process and measurement noise. We are motivated by the future of autonomy where robots will autonomously perform complex tasks despite unknown and unpredictable disturbances leveraging their on-board control and sensing capabilities. To synthesize our minimal-regret controller, we formulate a constrained semi-definite program based on a System Level Synthesis approach for partially-observed time-varying systems. We validate our algorithm in simulated scenarios, including trajectory tracking scenarios of a hovering quadrotor collecting GPS and IMU measurements. Our algorithm is observed to have better performance than either or both the $\mathcal{H}_2$ and $\mathcal{H}_\infty$ controllers, demonstrating a Best of Both Worlds performance.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Safe and Efficient Switching Controller Design for Partially Observed Linear-Gaussian Systems
Switching control strategies that unite a potentially high-performance but uncertified controller and a stabilizing albeit conservative controller are shown to be able to balance safety with efficiency, but have been les…
Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems
Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity. Stability is a crucial property for safety-critical dynamical systems, while stabilization of partially observ…
LEMMALearning Over Contracting and Lipschitz Closed-Loops for Partially-Observed Nonlinear Systems (Extended Version)
This paper presents a policy parameterization for learning-based control on nonlinear, partially-observed dynamical systems. The parameterization is based on a nonlinear version of the Youla parameterization and the rece…
Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
Many systems contain latent variables that make their dynamics partially unidentifiable or cause distribution shifts in the observed statistics between offline and online data. However, existing control techniques often …
Safe Q-learning for continuous-time linear systems
Q-learning is a promising method for solving optimal control problems for uncertain systems without the explicit need for system identification. However, approaches for continuous-time Q-learning have limited provable sa…
Q-Learning