I received my Ph.D. degree from Institute of Automation, Chinese Academy of Sciences (CASIA). During my Ph.D., my main work includes two aspects:
1) Development of memory-based learning methods for a 5-DoF ping-pong playing robot. These learning methods focus on the learning ability, the execution efficiency and data storage.
2) Integration of physical knowledge, human experience and memory-based learning approaches in the robotic system. The integration is able to make full use of available information such that a higher robot performance is achieved.
Currently, I work on a 7-DoF robot arm and implement it for the table tennis task. My research interest includes control theory, machine learning and their applications to robotic systems.
A 7-DoF Ping-Pong Playing Robot (Aug. 2013 - Now)
My current project focuses on developing a more general setup for a 7-DoF robot table tennis. Meanwhile, I am also trying to introduce both causal structure and causal strength into our robotic system, so that the high dimensional learning is accelerated within a more compact search space.
A 5-DoF Ping-Pong Playing Robot (Sep. 2010 - Jul. 2013)
During my Ph.D., I worked on a 5-DoF ping-pong playing robot in the Institute of Automation, Chinese Academy of Sciences (CASIA). Please see the video in this website.
 Huang, Y.; Schölkopf, B.; Peters, J.; Learning Optimal Striking Points for a Ping-Pong Playing Robot, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, pp. 4587-4592, 2015.
 Huang, Y.; Xu, D.; Tan, M.; Su, H.; Adding Active Learning to LWR for Ping-Pong Playing Robot, IEEE Transactions on Control Systems Technology (TCST), 21(4), pp. 1489-1494, 2013.
 Huang, Y.; Xu, D.; Tan, M.; A Parallel Fuzzy Learning Approach to Determine the Hitting Point for Ping-Pong Playing Robot, International Journal of Innovative Computing Information and Control (IJICIC), 9(10), pp. 4181-4192, 2013.
 Huang, Y.; Xu, D.; Tan, M.; Su, H.; Trajectory Prediction of Spinning Ball for Ping-Pong Player Robot, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), San Francisco, USA, pp. 3434-3439, 2011.
A 5-DoF Ping-Pong Playing Robot
The 5-DoF ping-pong playing robot was developed in the Institute of Automation, Chinese Academy of Sciences, where I received my PhD degree. In this video, the problem of controlling the racket attached to the ping-pong playing robot is considered, so that the incoming ball is returned to a desired position (the small red area).
A General Setup for A 7-DoF Robot Table Tennis
In this video, a more general setup for a 7-DoF robot table tennis was proposed, where the table tennis task is formulated as a regression problem.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems