No âmbito da 3ª edição do Ciclo de Palestras por Jovens Doutorados (DEEC-JD3), irá realizar-se no próximo dia 29 de janeiro de 2020, às 12:30, no anfiteatro EA3, a 1ª palestra do ciclo.

Título: Planning for Mobile Robots with Probabilistic Performance Guarantees

Orador: Bruno Lacerda, Senior Researcher in Robotics, University of Oxford

Resumo: Robust mission planning algorithms for autonomous robots typically require explicit reasoning and prediction of the inherent uncertainty of environmental features. For example, service robots need to consider the behaviour of humans around them; autonomous underwater vehicles require models of underwater currents; and robots in a multi-robot system need to reason about how interaction with other robots can affect their performance. In this talk, I will provide an overview of recent research on the synthesis of robust and intelligent robot behaviour using a range of techniques from probabilistic planning and formal methods. I will start by presenting work on planning for mobile service robots modelled as Markov decision processes, where the goal specification is given in co-safe linear temporal logic. I will then describe how this work has been the basis for the development of several research directions. In particular, I will discuss richer, multi-objective, specifications; multi-robot planning; and richer models of uncertainty. I will finish by discussing my overall research goal of unifying these different directions to obtain planning and coordination mechanisms for teams of robots modelled using rich models of uncertainty, and with rich sets of goal specifications.