Tingguang Li （李珽光）

tgli0809 AT gmail.com


I am currently a Senior Research Scientist at Robotics X Lab, Tencent. Before that, I received the Ph.D. degree at The Chinese University of Hong Kong, supervised by Professor Max Qing-Hu Meng, and the BEng. from Nanjing University. In 2019, I was a Visiting Student Researcher at Artificial Intelligence Laboratory (SAIL), Stanford University, under the supervision of Professor Jeannette Bohg.

My research interests lie in applying Reinforcement Learning on Robotics, including dexterous manipulation, quadrapdal control, decision making, imitation learning, sim-to-real transfer. Recently, I am working on projects of multimodal models, specifically, Vison Language Action models (VLA). We hope to endow robots with the intelligence to see (Vision), listen (language) and react (Action) autonomously.

!!!We are hiring self-motivated interns. If you are working on deep reinforcement learning, robotics, and interested in large models, please feel free to contact me.

Google Scholar  |  CV  |  Github  |  Linkedin

News




Journal Papers

Lifelike Agility and Play on Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
Lei Han*, Qingxu Zhu*, Jiapeng Sheng*, Chong Zhang*, Tingguang Li*, Yizheng Zhang*, He Zhang*, Yuzhen Liu, Cheng Zhou, Rui Zhao, Jie Li, Yufeng Zhang, Rui Wang, Wanchao Chi, Xiong Li, Yonghui Zhu, Lingzhu Xiang, Xiao Teng, Zhengyou Zhang.
(Nature Machine Intelligence, Vol. 6, No. 7, 2024, the Cover Article)
Project Page ·  Nature ·  Arxiv ·  Video Demo (YouTube)

GMR-RRT*: Sampling-based Humanlike Path Planning Using Gaussian Mixture Regression
Jiankun Wang, Tingguang Li, Baopu Li, Max Q.-H. Meng.
(IEEE Transactions on Intelligent Vehicles 2022)

Learning Robot Exploration Strategy with 4D Point-Clouds-like Information as Observations
Zhaoting Li, Tingguang Li, Jiankun Wang, Max Q.-H. Meng.
(IEEE Robotics and Automation Letters 2021)

An Autonomous Eye-in-hand Robotic System for Elevator Button Operation Based on Deep Recognition Network
Delong Zhu, Zhe Min, Tong Zhou, Tingguang Li, Max Q.-H. Meng.
(IEEE Transactions on Instrumentation & Measurement 2020)

A Searching Space Constrained Partial to Full Registration Approach with Applications in Airport Trolley Deployment Robot
Jin Pan, Xiaochun Mai, Chaoqun Wang, Zhe Min, Jiankun Wang, Hu Cheng, Tingguang Li, Erli Lyu, Li Liu, Max Q.-H. Meng.
(IEEE Sensor Journal 2020)



Conference Papers

An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement
Haojie Shi*, Tingguang Li*, Qingxu Zhu, Jiapeng Sheng, Lei Han, Max Q.-H. Meng.
(IEEE International Conference on Robotics and Automation, ICRA 2024)
Paper ·  Video Demo (YouTube)

Learning Highly Dynamic Behaviors for Quadrupedal Robots
Chong Zhang, Jiapeng Sheng, Tingguang Li, He Zhang, Cheng Zhou, Qingxu, Zhu, Rui Zhao, Yizheng Zhang, Lei Han.
(IEEE International Conference on Robotics and Automation, ICRA 2024)
Paper

Learning Terrain-Adaptive Locomotion with Agile Behaviors by Imitating Animals
Tingguang Li, Yizheng Zhang, Chong Zhang, Qingxu Zhu, Jiapeng Sheng, Cheng Zhou, Lei Han.
(IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023)
Paper ·  Video Demo (YouTube)

HouseExpo: A Large-scale 2D Indoor Layout Dataset for Learning-based Algorithms on Mobile Robots
Tingguang Li, Danny Ho, Chenming Li, Delong Zhu, Chaoqun Wang, Max Q.-H. Meng.
(IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020)
Project Page · Paper ·  Video Demo (YouTube) · Code (Github)

Learning Hierarchical Control for Robust In-Hand Manipulation
Tingguang Li, Krishnan Srinivasan, Max Q.-H. Meng, Wenzhen Yuan, Jeannette Bohg.
( IEEE International Conference on Robotics and Automation, ICRA 2020)
Project Page · Paper ·  Video Demo (YouTube)· Code (Github)

Solving a Rubik's Cube with a Dexterous Hand
Tingguang Li, Weitao Xi, Meng Fang, Jia Xu, Max Q.-H. Meng.
(IEEE International Conference on Robotics and Biomimetics, ROBIO 2019)
Project Page · Paper ·  Video Demo (YouTube) · Code (Github)

A Novel OCR-RCNN for Elevator Button Recognition
Delong Zhu, Tingguang Li, Danny Ho, Tong Zhou, Max Q.-H. Meng.
(IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018)
Paper ·  Video Demo (YouTube) · Code (Github)

Deep Reinforcement Learning Supervised Autonomous Exploration in Office Environment
Delong Zhu*, Tingguang Li*, Danny Ho*, Chaoqun Wang, Max Q.-H. Meng.
( IEEE International Conference on Robotics and Automation, ICRA 2018)
Paper ·  Video Demo (YouTube) *indicates equal contribution.

Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration
Tingguang Li, Jin Pan, Delong Zhu, Max Q.-H. Meng.
(IEEE International Conference on Robotics and Biomimetics, ROBIO 2018)
Paper

A Hybrid 3DoF Pose Estimation Method Based on Camera and Lidar Data
Tingguang Li, Delong Zhu, Max Q.-H. Meng.
(IEEE International Conference on Robotics and Biomimetics, ROBIO 2017, Best Conference Paper Award Finalist)
Project Page · Paper ·  Video Demo (YouTube) ·  Code (Github)

Bone Drilling Breakthrough Detection via Energy-based Signal
Danny Ho, Tingguang Li, Max Q.-H. Meng.
(International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018)
Paper



Research Projects

ICRA 2017 DJI RoboMaster Manipulation Challenge (5/93)
Developed a mobile manipulator which can autonomously detect, pick, transport, and stack the target cubes. In the final competition we successfully piled up 10 cubes and ranked 5th place.
Video Demo (YouTube)



Talks




Honors





Teaching