Reliable Plan Selection with Quantified Risk-Sensitivity

Tobias John, Mahya Mohammadi Kashani, Jeremy P Coffelt, Einar Broch Johnsen, Andrzej Wasowski

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review


Robots in many domains need to plan and make decisions under uncertainty; for example, autonomous underwater vehicles (AUVs) gathering data in environments inaccessible to humans, need to perform automated task planning. Planning problems are typically solved by risk-neutral optimization maximizing a single objective, such as limited time or energy consumption. A typical probabilistic planner synthesizes a plan to reach the desired goals with a maximum expected reward, given the possible initial states and actions of the world. In this work, we additionally consider risk metrics for selecting solutions to such planning problems. Consider a marine robotics mission scenario where the task is to survey pipeline segments safely based on various risk measurements.
TitelNWPT 2023 - 34th Nordic Workshop on Programming Theory
StatusUdgivet - 2023
BegivenhedNWPT 2023 - 34th Nordic Workshop on Programming Theory - Mälardalen University, Västerås, Sverige
Varighed: 22 nov. 202323 nov. 2023


WorkshopNWPT 2023 - 34th Nordic Workshop on Programming Theory
LokationMälardalen University
By Västerås


Dyk ned i forskningsemnerne om 'Reliable Plan Selection with Quantified Risk-Sensitivity'. Sammen danner de et unikt fingeraftryk.