Lyu Erli, Ph.D., is currently a lecturer at the Faculty of Applied Sciences, Macau Polytechnic University. Dr. Lyu obtained his Ph.D. in Mechanical Engineering from Harbin Institute of Technology (Shenzhen) in 2023. He has published more than ten academic papers in renowned international journals and conferences such as IEEE Transactions on Automation Science and Engineering and IROS. Dr. Lyu was awarded the second and the golden egg prize at the Jingdong X robotics challenge as the team leader, and was awarded the IEEE-ROBIO 2021 T.J. Tarn Best Robotics Paper Award as a co-first author.

[1] Lyu E, Liu T, Wang J, Song S, Meng MQ. Motion planning of manipulator by points-guided sampling network. IEEE Transactions on Automation Science and Engineering. 2022 Apr 29;20(2):821-31.
[2] Zhang Z, Lyu E*, Min Z, Zhang A, Yu Y, Meng MQ. Robust Semi-Supervised Point Cloud Registration via Latent GMM-Based Correspondence. Remote Sensing. 2023 Sep 12;15(18):4493.
[3] Lyu E, Zhang Z, Liu W, Wang J, Song S, Meng MQ. MO-Transformer: A Transformer-Based Multi-Object Point Cloud Reconstruction Network. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022 Oct 23 (pp. 1024-1030). IEEE.
[4] Lyu E, Zhang Z, Wang J, Song S, Meng MQ. Towards Components-of-Interest Feedback Control and State Estimation of Robotic Manipulator. In 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO) 2021 Dec 27 (pp. 539-544). IEEE.
[5] Lyu E, Yang X, Liu W, Wang J, Song S, Max QH. AN AUTONOMOUS EYE-IN-HAND ROBOTIC SYSTEM FOR PICKING OBJECTS IN A SUPERMARKET ENVIRONMENT WITH NON-HOLONOMIC CONSTRAINT. International Journal of Robotics and Automation. 2022 Jan 1;37(4).
[6] Liu T#, Lyu E#, Wang J, Meng MQ. Unified Intention Inference and Learning for Human–Robot Cooperative Assembly. IEEE Transactions on Automation Science and Engineering. 2021 May 17;19(3):2256-66.
[7] Zhou T, Qi S, Lyu E#, Cen G, Wang J, Meng MQ. Towards Minimally-Intrusive Navigation in Densely-Populated Pedestrian Flow. In 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO) 2021 Dec 27 (pp. 334-339). IEEE.

Selected publications, # co-first author, * correspondence author

My research focuses on using environmental information to achieve highly efficient motion planning. This process usually involves two main components: a point cloud autoencoder to extract environmental representation from the point cloud through unsupervised reconstruction, and a sampling network to predict a multi-density distribution for the next configuration state based on the extracted representation. It is closely related to point cloud autoencoder and neural motion planning. I'm also interested in densely-populated pedestrian navigation, autonomous driving, and human-robot cooperation.

My research interests include:
- Neural motion planning;
- Point cloud autoencoder;
- Non-conservative autonomous driving;
- Densely-populated pedestrian navigation;
- Reinforcement learning (MCTS, etc.);
- Human-robot cooperation
- Other deep learning applications;

I recruit MSc students every year, and I particularly welcome students who are interested in pursuing a doctoral degree after graduation. If you are prospective Ph.D. student and you are interested in my research, please feel free to contact me directly by email with your CV attached.