Note: Yanlong Huang has transitioned from the institute (alumni).
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.
Key References
[1] 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.
[2] 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.
[3] 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.
[4] 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.