Abstract
AbstractAutonomous robots used in infrastructure inspection, space exploration and other critical missions operate in highly dynamic environments. As such, they must continually verify their ability to complete the tasks associated with these missions safely and effectively. Here we present a Bayesian learning framework that enables this runtime verification of autonomous robots. The framework uses prior knowledge and observations of the verified robot to learn expected ranges for the occurrence rates of regular and singular (e.g., catastrophic failure) events. Interval continuous-time Markov models defined using these ranges are then analysed to obtain expected intervals of variation for system properties such as mission duration and success probability. We apply the framework to an autonomous robotic mission for underwater infrastructure inspection and repair. The formal proofs and experiments presented in the paper show that our framework produces results that reflect the uncertainty intrinsic to many real-world systems, enabling the robust verification of their quantitative properties under parametric uncertainty.
Publisher
Springer Science and Business Media LLC
Reference63 articles.
1. The Headquarters for Japan’s Economic Revitalization. New Robot Strategy: Japan’s Robot Strategy. Prime Minister’s Office of Japan (2015).
2. SPARC–The Partnership for Robotics in Europe. Robotics 2020 multi-annual roadmap for robotics in Europe. eu-robotics (2016).
3. Science and Technology Committee. Robotics and Artificial Intelligence. Committee Reports of UK House of Commons (2016).
4. Christensen, H. et al. A roadmap for us robotics–from internet to robotics 2020 edition. Found. Trends Robot. 8, 307–424 (2021).
5. Richardson, R. et al. Robotic and autonomous systems for resilient infrastructure. UK-RAS White Papers© UK-RAS (2017).