Towards Explainable and Trustworthy Autonomous Systems

ZOOM Link: https://brookes.zoom.us/j/83370496802

The next Oxford Artificial Intelligence Meetup is on Monday the 14th of March 19:00-21:00 on Zoom.

Dr Kunze will be speaking on the topic "Towards Explainable and Trustworthy Autonomous Systems".

Autonomous systems operating in real-world environments are required to understand their surroundings, assess their capabilities, and explain what they have seen, what they have done, what they planning to do, and why to different stakeholders including end-users, developers, and regulators. In this talk, I will present and discuss our results and objectives from three research projects: SAX [1], RoAD [2], and RAILS [3]. In our work, we focus on autonomous vehicles and their application in challenging, open-ended environments. As it is essential that these systems are safe and trusted, we design, develop, and evaluate fundamental technologies in simulation and real-world applications to overcome critical barriers which impede the current deployment of autonomous vehicles in economically and socially important areas.

[1] https://ori.ox.ac.uk/projects/sense-assess-explain-sax/
[2] https://ori.ox.ac.uk/projects/road/
[3] https://ori.ox.ac.uk/projects/rails/

About Lars Kunze:

Lars Kunze is a Departmental Lecturer in Robotics within the Oxford Robotics Institute (ORI) in the Department of Engineering Science at Oxford University. In the ORI, he leads the Cognitive Robotics Group (CRG). Dr Kunze is also the Technical Lead at Oxford’s Responsible Technology Institute (RTI) and a Programme Fellow of the Assuring Autonomy International Programme (AAIP) at York University.

Within UKRI's Trustworthy Autonomous Systems (TAS) programme, he currently leads the RAILS project (Responsible AI for Long-term Trustworthy Autonomous Systems) and he is a Co-I in the RoAD project (Responsible AV Data). Recently, he completed the SAX project (Sense-Assess-eXplain) within the AAIP which investigated alternative sensing, performance assessments, and methods for explainability in autonomous driving.

His areas of expertise lie in the fields of robotics and artificial intelligence (AI). His goal is to enable systems to understand their surroundings, to act autonomously, and to explain their own behaviour in meaningful human terms. To this end, his research concerns the design and development of fundamental AI techniques for trustworthy autonomous systems.

Dr Kunze studied Cognitive Science (BSc, 2006) and Computer Science (MSc, 2008) at the University of Osnabrück, Germany, and partly at the University of Edinburgh, UK. He received his PhD (Dr. rer. nat.) from the Technical University of Munich, Germany, in 2014. Afterwards, he was appointed as a Research Fellow in the Intelligent Robotics Lab at the School of Computer Science at Birmingham University. He was a visiting researcher in the JSK Lab at the University of Tokyo, Japan (2011) and the Human-Robot Interaction Laboratory at Tufts University, US (2015). In 2017, he joined the ORI at Oxford University.