Abstract
In activities such as planetary exploration, work in nuclear plants, or disaster intervention, the dynamics of the environment and the strong constraints on data transmissions call for advanced robot autonomy. In this paper we propose a cooperative robot control system architecture based on a non-deterministic planner. We show how a traditional representation scheme, given a new semantics and a typology of operators (actions and events), can be called upon in order to take into account action failure and non-determinism as well as the world reactivity. We define the notion of robustness with respect to a safety condition and propose a linear search algorithm for producing robust plans. We show how we can limit the search by preparing for replanning in non-critical situations, thereby constructing a kind of minimal plan. Finally, we discuss plan execution and give hints of possible future developments.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
