Model-Free Stochastic Reachability Using Kernel Distribution Embeddings
| Autor: | Adam J. Thorpe, Meeko M. K. Oishi |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Control and Optimization Markov kernel Markov chain Computer science Stochastic process Recursion (computer science) 020206 networking & telecommunications Systems and Control (eess.SY) 02 engineering and technology Conditional probability distribution Electrical Engineering and Systems Science - Systems and Control 020901 industrial engineering & automation Optimization and Control (math.OC) Control and Systems Engineering Kernel (statistics) FOS: Mathematics FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering Applied mathematics Embedding Mathematics - Optimization and Control Reproducing kernel Hilbert space |
| Zdroj: | IEEE Control Systems Letters. 4:512-517 |
| ISSN: | 2475-1456 |
| DOI: | 10.1109/lcsys.2019.2954102 |
| Popis: | We present a solution to the terminal-hitting stochastic reach-avoid problem for a Markov control process. This solution takes advantage of a nonparametric representation of the stochastic kernel as a conditional distribution embedding within a reproducing kernel Hilbert space (RKHS). Because the disturbance is modeled as a data-driven stochastic process, this representation avoids intractable integrals in the dynamic recursion of the reach-avoid problem since the expectations can be calculated as an inner product within the RKHS. We demonstrate this approach on a high-dimensional chain of integrators and on Clohessy-Wiltshire-Hill dynamics. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|