Yidan Lu (鲁一丹)

personal_imgs/lyd.png

Hong Kong SAR, China. 999077

Email: ydlu@connect.hku.hk

I am a PhD student at The University of Hong Kong, affiliated with the ArcLab under the supervision of Professor Peng Lu. My research lies at the intersection of reinforcement learning and legged robotics, with a focus on enabling humanoid robots to learn from real-world interactions and acquire human-like capabilities.

I earned my Bachelor’s degree from Northwestern Polytechnical University in 2023, where I conducted research in audio speech recognition (ASR) under the guidance of Professor Lei Xie at the ASLP Lab. My work focused on enhancing the accuracy and efficiency of speech recognition systems.

I am passionate about advancing robotics to bridge the gap between technology and human society, aiming to automate repetitive tasks and unlock new possibilities for human potential.

Email / Google Scholar / Github / Linkedin

news

Jun 05, 2026 Very happy to attend ICRA 2026 in Vienna!
Oct 22, 2025 Honored to meet Marco Hutter at IROS 2025, Hangzhou, China!
Apr 24, 2025 Our recent paper “FR-Net: Learning Robust Quadrupedal Fall Recovery on Challenging Terrains through Mass-Contact Prediction” has been accepted by RAL! :sparkles: :smile:

Publications

ROOF: Learning Humanoid Fall Recovery under Overhead Constraints
Yidan Lu, Jiayuan Yu, Zongrui Cai, Jingwen Sun, Jinrui Han, Jing Wang, Ping Luo, Peng Lu†


In submission

RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning
Yichao Zhong*, Yidan Lu*, Yuhang Lu, Tianyang Tang, Haoguang Mai, Yixuan Pan, Tianyu Li, Li Chen, Jingbo Wang, Zhongyu Li, Peng Lu, Hongyang Li

CoRL 2026 (Oral 🏆)

Switch-JustDance: Benchmarking Whole-Body Motion Tracking Policies Using a Commercial Console Game
Jeonghwan Kim1*, Wontaek Kim1*, Yidan Lu2,7*, Jin Cheng3*, Fatemeh Zargarbashi3*, Zicheng Zeng4*, Zekun Qi5*, Zhiyang Dou6, Nitish Sontakke7, Donghoon Baek1, Sehoon Ha1, Tianyu Li1,

CVPR Findings 2026
Webpage | Arxiv | Code | Youtube | Bilibili

Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion
Yidan Lu1,2*, Rurui Yang2*, Qiran Kou2*, Mengting Chen2†, Tao Fan2, Peter Cui2, Yinzhao Dong1, Peng Lu1§,

arXiv Sep 2025
Webpage | Arxiv | Youtube | Bilibili

MGDP: Mastering a Generalized Depth Perception Model for Quadruped Locomotion
Yinzhao Dong*, Ji Ma*, Yidan Lu, Jiahui Zhang, Wanyue Li, Yeke Chen, Teng Zhang, Xuechao Chen, Zhangguo Yu, Peng Lu†

Advanced Science 2026

FR-Net: Learning Robust Quadrupedal Fall Recovery on Challenging Terrains through Mass-Contact Prediction
Yidan Lu*, Yinzhao Dong*, Jiahui Zhang, Ji Ma, Peng Lu†,

IEEE Robotics and Automation Letters (RA-L) 2025
IROS 2025 Presentation
Webpage | Paper | Arxiv | Code | Youtube | Bilibili

Projects

Autonomous Table Tennis for the AGIBOT A3 Humanoid
Kinetix AI Research Collaboration
Supervised by Ping Luo (MMLab@HKU)

Successor to SMASH. An autonomous table tennis system on the full-sized AGIBOT A3 humanoid that unifies ball state estimation, strike planning, and a motion-prior RL policy for whole-body racket-ball contact, July 2026 – present.

Tracking-Based Whole-Body Dance Control for Humanoid Robots
Team members: Mengting Chen, Yidan Lu, Yiran Ju, Rurui Yang, Qiran Kou, Tao Fan, Peter Cui

A tracking-based whole-body motion control policy that enables a humanoid robot to follow dance motions with coordinated upper- and lower-body movement, April 2025.

Learning Humanoid Perceptive Locomotion over Risky Terrain
Team members: Yidan Lu*, Rurui Yang*, Mengting Chen, Tao Fan, Peter Cui

A perception-based RL controller for humanoid robots on risky terrains, such as gaps, sparse footholds, and narrow walkways, December 2025.