Research Talks and a Networking Lunch on Physical Human-Robot Interaction at BRL

Agenda
Lunch session

12:00 – 14:30 : Networking lunch (Venue TBD)

Afternoon session (BRL Seminar Room)

14:30 – 15:00 : Welcome and Introduction by Tactile Robotics group

15:00 – 15:40 : Invited talk + Q&A

15:40 – 15:55 : Coffee break

15:55 – 16:35 : Invited talk + Q&A

16:35 – 17:15 : Invited talk + Q&A

17:15 – 18:00 : Open discussion

Invited Talks:

Robot Learning for Intelligent Assistants – Georgia Chalvatzaki

Societal factors like the increase in the elderly population, the lack of nursing staff, the hectic rhythms of everyday life, and the Covid-19 pandemic, make the need for intelligent robotic assistants more urgent than ever. This talk covers human activity recognition and understanding; the combination of classical and machine learning methods for robot action planning and control; reinforcement learning methods for adaptive Human-Robot Interaction (HRI); and methods for learning to plan long-horizon tasks. 

Control methods for physical human-robot interaction applications – Zoe Doulgeri

Over the last few decades, industrial robots have been widely deployed in the manufacturing industry, relieving workers from repetitive, unhealthy or arduous jobs with their workspace being strictly separated from that of humans for safety. Collaborative robots is a new generation of industrial robots that can work along side and with humans as co-workers or assistants. 

Learning Adaptive Motor Skills for Dexterous Manipulation and Grasping – Zhibin (Alex) Li

This talk will focus on machine learning based approaches for achieving autonomous manipulation and grasping capabilities. I will cover the topics of (1) learning reactive reaching and grasping of flying objects; (2) learning bimanual manipulation with direct sim2real transfer; (3) learning from real data of a handful of human demonstrations; and (4) how novel tactile sensors with soft embodiment design can help learning dexterous and fine motor skills without the need of computationally intensive simulations.

Speaker Bios:

Dr. Georgia Chalvatzaki is an Assistant Professor and the research leader of the intelligent robotic systems for assistance (iROSA) group at TU Darmstadt. She received the Emmy Noether grant from the German Research Foundation (DFG) in 2021. In iROSA, her team researches the topic of “Robot Learning of Mobile Manipulation for Intelligent Assistance,” investigating novel methods for combined planning and learning to enable mobile manipulator robots to solve complex tasks in house-like environments with the human-in-the-loop of the interaction process.

Lab website: iROSA lab

Zoe Doulgeri is a Professor of Robotics and Control of Manufacturing Systems in the Automation and Robotics Lab of the Department of Electrical and Computer Engineering of the Aristotle University of Thessaloniki (AUTH).  She teaches Control Systems and Robotics, and has authored more than 150 publications in peer-reviewed international journals and conferences.

Her current research interests include the topics of physical human robot interaction, robot teaching and learning by demonstration, bimanual mobile robots, object grasping and manipulation with analytical and data based learning methods and the control of uncertain robotic systems.

Lab website: Automation and Robotics Lab

Zhibin (Alex) Li is an Associate Professor at the University College London and leads the Advanced Robotics Intelligence Laboratory. His work in 2019-2020 – “multi-expert learning of adaptive legged locomotion” – is the first implementation of a multi-expert learning architecture for adaptive quadrupedal locomotion on a real robot (selected as the cover for December 2020 issue of Science Robotics).

His research interest covers dynamic motion skills of locomotion and manipulation, optimization-based motion planning and control, and deep reinforcement learning for robot motor learning including locomotion, manipulation and grasping.

Lab website: Advanced Intelligent Robotics Lab