Safe Learning for Uncertainty-Aware Planning via Interval MDP Abstraction
| Autor: | Jiang, Jesse, Zhao, Ye, Coogan, Samuel |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | IEEE Control Systems Letters, vol. 6, pp. 2641-2646, 2022 |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1109/LCSYS.2022.3173993 |
| Popis: | We study the problem of refining satisfiability bounds for partially-known stochastic systems against planning specifications defined using syntactically co-safe Linear Temporal Logic (scLTL). We propose an abstraction-based approach that iteratively generates high-confidence Interval Markov Decision Process (IMDP) abstractions of the system from high-confidence bounds on the unknown component of the dynamics obtained via Gaussian process regression. In particular, we develop a synthesis strategy to sample the unknown dynamics by finding paths which avoid specification-violating states using a product IMDP. We further provide a heuristic to choose among various candidate paths to maximize the information gain. Finally, we propose an iterative algorithm to synthesize a satisfying control policy for the product IMDP system. We demonstrate our work with a case study on mobile robot navigation. Comment: 8 pages, 3 figures; accepted to IEEE Control Systems Letters |
| Databáze: | arXiv |
| Externí odkaz: |
|