Seminar Artificial Intelligence - Dr. H. Kasei

Title: Interactive Robot Learning in Open-Ended Domains.

Abstract:

While a lot of developments have been made in the field of robotics, computer vision, and machine learning, service robots do not yet live among humans to assist in various daily tasks. The underlying reason is that robots are usually painstakingly coded and trained in advance to perform object perception and manipulation tasks in the right way. Moreover, they are trained once all data has been gathered, making them strongly dependent on the quality and quantity of training data. Therefore, the knowledge of such robots is fixed after the training phase, and any changes in the environment require complicated, time-consuming, and expensive robot re-programming by expert users.

In human-centric environments, it is not feasible to assume that one can pre-program all necessary object categories and grasp templates for the robots. To operate in such dynamic environments, I believe an appropriate approach is to make robots capable of learning in an open-ended fashion by interacting with non-expert users. In this talk, I will give a brief overview of my research on 3D object perception and manipulation before diving into one of my latest research on “Simultaneous Multi-View Object Grasping and Recognition in Open-Ended Domains”. In this project, “open-ended” implies that the set of object categories to be learned is not completely known in advance. The training instances are extracted from online experiences of a robot, and become gradually available over time. Moreover, apart from robot self-learning, non-expert users could interactively guide the process of experience acquisition by teaching new concepts, or by correcting insufficient or erroneous concepts. In this way, the robot will constantly learn how to help humans in everyday tasks by gaining more and more experiences without the need for re-programming.