SEMINAR - Angela Faragasso (University of Tokyo): Toward Reproducible Research: Benchmarking and Verification in Medical and Remote-Controlled Rescue Robotics
In robotics research the Replicability and Reproducibility (RR) of results and their objective evaluation and comparison is seldom practiced. This situation impairs both research progress and technology transfer. Although significant progress has been made in recent years, reproducibility of robotics and AI research is still in its infancy, and this prevents serious development in benchmarking and verification of intelligent systems as the related scientific ground is unstable. Additional challenges arise in medical and rescue robotics in which remote-controlled machines are replacing humans in hazardous and dangerous tasks. In this talk I will first discuss my personal experience in the area of artificial tactile feedback, an active field of applied research which aims to retrieve the human sense of touch and feedback information on external objects by employing sensing mechanism with robotics devices. I will present the steps toward the realisation of a versatile system, which can be embedded at the tip of a generic camera and fashioned for different robotic applications, underlining the challenge which arises in its RR for minimally invasive medical robotic systems. After, I will introduce the remote-controlled technologies developed in response to the disaster caused by the earthquake and tsunami of 11 March 2011 in the Fukushima Daiichi Nuclear Power Plant, and propose possible solutions to reproducible and uniform research.
Bio: Angela Faragasso received the MSc degree in Artificial Intelligence and Robotics from Sapienza University of Rome in 2012. During her master she joined for one year the Center for Robot-Assisted Search and Rescue (CRASAR) at the Texas A&M University. Her PhD project started in late 2012 at the Centre for Robotics Research, King’s College London and was funded by the EPSRC and the EU FP7 project STIFF-FLOP. In November 2016 she won a JSPS postdoctoral research fellowship and joined the Service Robotics Laboratory at the University of Tokyo, where in April 2019 she was promoted to assistant professor. Since 2018 Dr Faragasso has been Associate Editor of the IEEE Robotics and Automation Magazine (RAM) and junior co-chair of the IEEE Technical Committee for Performance Evaluation & Benchmarking of Robotic and Automation Systems (TC-PEBRAS). Her research activities involve different fields of robotics applications, such as medical, rescue and automation. A constant in her research is the use of image processing algorithms to perform autonomous control or to understand properties of objects in the environment, i.e. stiffness, in real-time. Additional research involves hybrid control, intelligent construction systems and bio-inspired robotics.