Improving Robustness of Robot Deployments in the Wild through Decision-Making under Uncertainty
Speaker: Bruno Lacerda
Senior Researcher in Robotics, University of Oxford
DEIB - 3B Room (Bld. 20)
December 13th, 2024 | 11.00 am
Contact: Prof. Francesco Amigoni
Senior Researcher in Robotics, University of Oxford
DEIB - 3B Room (Bld. 20)
December 13th, 2024 | 11.00 am
Contact: Prof. Francesco Amigoni
Sommario
On December 13th, 2024 at 11.00 am the seminar titled "Improving Robustness of Robot Deployments in the Wild through Decision-Making under Uncertainty" will take place at DEIB 3B Room (Building 20).
In this talk, I will discuss several works developed in the GOALS Lab at the Oxford Robotics Institute that aim to improve the robustness of robot systems deployed in the wild.
In particular, I will discuss a set of techniques that increase robustness to epistemic uncertainty by synthesising policies that adapt to the environmental conditions under which the robot will execute its mission. These techniques include Bayes-adaptive planning; constrained, worst-case and risk-aware optimisation; training approaches for reinforcement learning that explicitly consider the environmental uncertainty; and reasoning about human operators in shared autonomy systems. I will present several works that use these techniques, both in the single and the multi-robot settings.
In this talk, I will discuss several works developed in the GOALS Lab at the Oxford Robotics Institute that aim to improve the robustness of robot systems deployed in the wild.
In particular, I will discuss a set of techniques that increase robustness to epistemic uncertainty by synthesising policies that adapt to the environmental conditions under which the robot will execute its mission. These techniques include Bayes-adaptive planning; constrained, worst-case and risk-aware optimisation; training approaches for reinforcement learning that explicitly consider the environmental uncertainty; and reasoning about human operators in shared autonomy systems. I will present several works that use these techniques, both in the single and the multi-robot settings.
Biografia
Bruno Lacerda is a Senior Researcher at the Oxford Robotics Institute, University of Oxford, UK. He 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.
His research focuses on the intersection of decision-making under uncertainty, formal methods, and mobile robotics. In particular, he is interested in using a combination of techniques from learning, planning and model checking to synthesise intelligent, robust and verifiable behaviour, for both single and multi-robot systems.
His research focuses on the intersection of decision-making under uncertainty, formal methods, and mobile robotics. In particular, he is interested in using a combination of techniques from learning, planning and model checking to synthesise intelligent, robust and verifiable behaviour, for both single and multi-robot systems.
