Seminar: Robust learning and control in Surgical robotics, 30th Nov, 1pm

When: Thursday 30th of Nov, 1pm AEDT

Where: This seminar will be partially presented at the Rose Street Seminar area (J04) and partially online via Zoom. RSVP

Speaker: Jing Cheng

Title: Robust Learning and Control in Surgical Robotics

Abstract:

Surgical robotics is a promising field of robotics research. Recent advances in deep learning and robotic imaging provide medical robot with an encouraging future. However, this field also comes with fundamental challenges.  The robot is expected to interact with patient tissue, which could be unknown or have complex dynamics, in the mean while it also has high requirements on safety. This underscores the imperative need for the robot controller to have flexibility as much as possible to deal with complex surgical tasks , also certain guarantee on the stability and robustness to meet the safety requirements. 

In this talk we suggest combining passivity theory and recent advances on machine learning could be a cure to this problem. With reasonable assumptions, a nonlinear controller with stability and robustness guarantees can be learnt,  which could achieve a safe interaction law between a robot and environment and have improved performance. 

Bio:

Jing (Johnny) Cheng received his bachelor’s degree at Harbin Institute of Technology (HIT) in 2014 and master’s degree at the University of Sydney in 2018. Currently he is a PhD candidate at Australian Centre for Field Robotics (ACFR), working on force control in surgical robotics. His research interest includes robust machine learning and non-linear control.