Shangding Gu, M.Sc.

E-Mail shangding.gu(at)tum.de
Address Boltzmannstr. 3
85748 Garching b. München
Gemany
Office hours appointment by email

Curriculum Vitae

I am a Ph.D. Candidate at the Chair of Robotics, Artificial Intelligence and Real-time Systems, under the supervision of Prof. Alois Knoll. Before studying in Munich, I was a research assistant at the Institute of Automation, Chinese Academy of Sciences, and Tongji University. I had a great time visiting Prof. Jan Peters’s Research Group at the Technical University of Darmstadt from Sep.2022 to Dec.2022. My research currently focuses on developing artificial intelligence methods and models, with a special interest in exploring the theory of safe reinforcement learning and motion planning, and its application in robotics, in which the goal is to enable robots to know how to learn, reason and plan, and enable robots to work in support of people.


Research Interests

  • Safe/Robust Reinforcement Learning; Reinforcement Learning Theory; AI Safety.
  • Motion Planning; Autonomous Driving; Robotics (e.g., arm robotics and marine robotics). 

Safe Reinforcement Learning Workshop

We organized a safe reinforcement learning workshop, the researchers and students who are interested in safe RL  are welcome to join us! The recorded videos are available on YouTube's Safe RL Channel, please see the YouTube Channel or  Workshop Homepage.


Safe Reinforcement Learning Online Seminar

In December 2022, we launched a long-term safe reinforcement learning online seminar. Every month, we will invite at least one speaker to share cutting-edge research with RL researchers and students (each speaker has about 1 hour to share his/her research). We believe that holding this seminar can  promote the research of safe reinforcement learning. For details, please see the Seminar Homepage.


Offered Thesis Topics

Ongoing Master Thesis Topics:

  • Stability analysis of safe reinforcement learning 
  •  A safe reinforcement learning method based on control theory
  • Privacy Risk Analysis for Synthetic Data

Finished Guided Research topic:

  •  A safe multi-agent reinforcement learning algorithm in robotics applications  

If you are interested in the above topics, please feel free to contact me indicating your background and skills.


Academic Service as a Reviewer

As a reviewer for some international conferences and journals:

  • ICML, NeurIPS, ICLR, AAAI, ICRA, IROS, AAMAS, UKRAS, ICARM 
  • Journal of Machine Learning Research
  • IEEE Transactions on Automation Science and Engineering
  • IEEE Transactions on Vehicular Technology
  • IEEE Transactions on Neural Networks and Learning Systems
  • IEEE Transactions on Intelligent Transportation Systems
  • IEEE Transactions on Artificial Intelligence
  • IEEE Transactions on Aerospace and Electronic Systems
  • IEEE Access
  • Journal of Navigation
  • Ocean Engineering
  • Applied Ocean Research
  • Journal of Engineering for the Maritime Environment
  • Intelligent Automation & Soft Computing, etc.

 


Demos