On-the-Fly Control of Unknown Systems: From Side Information to Performance Guarantees Through Reachability
- 26 October 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 68 (8) , 4857-4872
Abstract
We develop data-driven algorithms for reachability analysis and control of systems with a priori unknown nonlinear dynamics. The resulting algorithms not only are suitable for settings with real-time requirements but also provide provable performance guarantees. To this end, they merge noisy data from only a single finite-horizon trajectory and, if available, various forms of side information. Such side information may include knowledge of the regularity of the dynamics, algebraic constraints on the states, monotonicity, or decoupling in the dynamics between the states. Specifically, we develop two algorithms, DaTaReach and DaTaControl , to over-approximate the reachable set and design control signals for the system on the fly. DaTaReach constructs a differential inclusion that contains the unknown dynamics. Then, in a discrete-time setting, it over-approximates the reachable set through interval Taylor-based methods applied to systems with dynamics described as differential inclusions. We provide a bound on the time step size that ensures the correctness and termination of DaTaReach . DaTaControl enables convex-optimization-based control using the computed over-approximation and the receding-horizon control framework. Besides, DaTaControl achieves near-optimal control and is suitable for real-time control of such systems. We establish a bound on its suboptimality and the number of primitive operations it requires to compute control values. Then, we theoretically show that DaTaControl achieves tighter suboptimality bounds with an increasing amount of data and richer side information. Finally, experiments on a unicycle, quadrotor, and aircraft systems demonstrate the efficacy of both algorithms over existing approaches.Keywords
All Related Versions
Funding Information
- Air Force Office of Scientific Research (FA9550-19-1-0005)
- National Aeronautics and Space Administration (80NSSC19K0209)
This publication has 33 references indexed in Scilit:
- Lipschitz optimisation for Lipschitz Interpolation2017
- Data-driven and model-based verification via Bayesian identification and reachability analysisAutomatica, 2017
- Forward Inner-Approximated Reachability of Non-Linear Continuous Systems2017
- Dynamic Mode Decomposition with ControlSIAM Journal on Applied Dynamical Systems, 2016
- Convex Optimization: Algorithms and ComplexityFoundations and Trends in Machine Learning, 2015
- Contractor programmingArtificial Intelligence, 2009
- Optimal estimation of univariate black-box Lipschitz functions with upper and lower error boundsComputers & Operations Research, 2003
- Constrained model predictive control: Stability and optimalityAutomatica, 2000
- Validated solutions of initial value problems for ordinary differential equationsApplied Mathematics and Computation, 1999
- On the Linear Convergence of Descent Methods for Convex Essentially Smooth MinimizationSIAM Journal on Control and Optimization, 1992