When: Thursday, April 29, 2021, 3pm (CEST).

Where: Zoom online, check the address in the Google Calendar Event.

Topic: Mission Planning for Mobile Robots with Probabilistic Performance Guarantees.

Speaker: Bruno Lacerda, Senior Researcher in Robotics, University of Oxford.

Abstract

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 our recent research on the synthesis of robust and intelligent robot behaviour using a range of techniques from probabilistic planning and formal methods. I will highlight two strands of work: planning with learnt models and planning for multi-robot coordination. For the former, I will cover our work on Gaussian process modelling on environmental features and on regret minimisation for uncertain Markov decision processes. For the latter, I will describe our efforts to model and reason about uncertain action durations in a principled fashion.

Short Bio

Bruno Lacerda received his Ph.D. in Electrical and Computing Engineering from the Instituto Superior Técnico, University of Lisbon, Portugal, in 2013. Between 2013 and 2017, he was a Research Fellow at the School of Computer Science, University of Birmingham, UK. Currently, he is a Senior Researcher at the Oxford Robotics Institute, University of Oxford, UK. His research focuses on the intersection of decision making under uncertainty, formal methods, and mobile robotics. In particular, he is interested in the use of a combination of techniques from learning, planning and model checking to synthesise intelligent, robust and verifiable behaviour, for both single and multi-robot systems.

Material

  • Video (Passcode: mA#XG!^3)