Safe and Efficient Human-Robot Collaboration
Date: 2021/11/16 - 2021/11/16
Academic Seminar: Safe and Efficient Human-Robot Collaboration
Speaker: Dr. Yujiao Cheng, Ph.D. candidate in the Department of Mechanical Engineering, University of California at Berkeley
Time: 9:00 a.m.-10:00 a.m., Nov 16th, 2021 (Beijing Time)
Location: via Feishu
Abstract
As the emphasis of manufacturing is shifting from mass production to mass customization, the demands for flexible automation keep increasing. Human-robot collaboration (HRC), as an effective and efficient way to enhance flexibility, has attracted lots of attention both in industry and academia in the past decade. These robots are called co-robots. The fundamental research question is how to ensure that co-robots operate efficiently and safely with human partners.
In this talk, two goals of my research will be discussed: 1) co-robots should know the human's intentions and take corresponding actions to ensure task efficiency, and 2) co-robots should know the human's future trajectory to avoid potential collisions and guarantee safety. To make this happen, a robotic system is adopted, which reasons about human behavior and makes human-aware planning. For reasoning about human behavior, a hierarchical probabilistic modeling method and two online adaptation algorithms are proposed for intention recognition and trajectory prediction. The hierarchical probabilistic modeling method explicitly utilizes the hierarchical behavior of the human and uses a pipeline to identify human intention through the trajectory, the motion type, the action, and finally the plan, which is explainable and data efficient. Two online adaptation algorithms are proposed for two trajectory prediction models respectively, where the recursive least square-parameter adaptation algorithm (RLS-PAA) is used to online adapt the last layer of a neural network model and the objective-based adaptation algorithm is used to online adapt the sigma-lognormal model. The adaptation algorithms enable the prediction models to accommodate different human behaviors and to deal with the lack of human data. For making human-aware planning, a parallel task planner is proposed, which uses the knowledge of human intention and makes the robot execute actions that are parallel to the human’s actions, while minimizing the task completion time. Different from those methods that only considers time efficiency, our parallel task planner additionally improves the human’s satisfaction and avoids potential conflicts, which can be shown in our experiment results. The overall robotic system is implemented on a FANUC LR Mate 200id/7L robot arm.
Biography
Yujiao Cheng is a Ph.D. candidate in the Department of Mechanical Engineering, University of California at Berkeley. She received the B.S. degree in Automation from the University of Science and Technology of China in 2016. Her research interests lie in the intersection of robotics, human-robot collaboration, control, optimization, and artificial intelligence. She was the recipient of the Chinese National Scholarship in 2014, Guo Moruo Scholoarship in 2015, and the Berkeley fellowship from 2016 to 2018. Her Ph.D. work has been supported by the Berkeley fellowship and FANUC Corporation.