Junfeng Long「龙俊峰」

Hello there! I am Junfeng Long, a research intern at Shanghai AI Laboratory. I am working on Reinforcement Learning and Robotics Control advised by Dr. Jiangmiao Pang.

I received my Bachelor degree in Computer Science at ShanghaiTech University. I worked with Prof. Youlong Wu as an undergraduate student on Information Theory and its Application in Distributed Systems.

Email: junfengac[AT]gmail[DOT]com

Google Scholar  |  Github  |  Twitter  

My research interest mainly falls on Reinforcement Learning, Optimization, Control and Robotics. I am particularly interested in the intersection of machine learning and control theory and apply them to real robotic systems to achieve agile and robust robotic locomotion, manipulation and interaction. I hope to bring together the strengths of machine learning (generalisability and computational friendliness) and control theory (robustness, theoretical guarantees) to push forward the frontier of robotic systems in the era of AI.

We present the H-infinity Locomotion Control, an adversarial framework improving the control policy's ability to resist external disturbances with H-infinity performance guarantee.

We present the Hybrid Internal Model, a method enabling the control policy to estimate environmental disturbances by only explicitly estimating velocity and implicitly simulating the system's response.

We propose a coded scheme to reduce the communication latency by exploiting computation and communication capabilities of all nodes and creating coded multicast opportunities.More importantly, we prove that the proposed scheme is always optimal, i.e., achieving the minimum communication latency, for arbitrary computing and storage abilities at the master.

Updated at Apr. 2024.
Template from Jon Barron.