Improvements in robot autonomy are changing human-robot interaction from low-level manipulation to high-level task-based collaboration. When a robot can independently and autonomously execute tasks, a human in a human-robot team acts as a collaborator or task supervisor instead of a tele-operator. When applying this to planning paths for a robotís motion, it is very important that the supervisorís qualitative intent is translated into a quantitative model so that the robot can produce a desirable consequence.
In the talk, I will present a framework that can transform a humanís qualitative requirement into a robotís quantitative model so that the robot behavior satisfies the humanís intent. It allows a human to express multi-objective, topological preferences, task plan and can be built to use language communication.
Daqing Yi is a Postdoc Fellow in the Personal Robotics Lab at Carnegie Mellon University. He has defended his Ph.D. dissertation (advised by Dr. Michael Goodrich) at the Department of Computer Science in Brigham Young University in August. He got his MS and BS degrees in Control Science and Engineering at Tongji University, China. His research interests include robotics, human-robot interaction and artificial intelligence.