I’m Jipeng KONG (孔继鹏), a Master’s student at School of Information Science and Technology, ShanghaiTech University (graduating 2027), supervised by Prof. Sören Schwertfeger. Currently, I’m an Intern at TeleAI, working on whole-body control for humanoid robots under the mentorship of Dr. Chenjia Bai.

My research focuses on humanoid robots, with an emphasis on:

• Robot Learning: Learning-based methods for skill acquisition
• Whole-Body Control: Coordinated control under physical constraints

I aim to build robust and transferable humanoid skills for real-world tasks.

Research & Work

• Pro-HOI: Perceptive Root-guided Humanoid-Object Interaction (arXiv, 2026)
  Paper Yuhang Lin, Jiyuan Shi, Dewei Wang, Jipeng Kong, Yong Liu, Chenjia Bai, Xuelong Li
  We introduce Pro-HOI, a generalizable framework for robust humanoid loco-manipulation. Our approach includes motion optimization, a novel policy conditioning scheme, and a perception module for reliable execution. Empirical validation on a Unitree G1 robot demonstrates significant improvements in generalization and robustness.

• Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework (arXiv, 2026)
  Paper | Project Page
  Jipeng Kong, Xinzhe Liu, Yuhang Lin, Jinrui Han, Sören Schwertfeger, Chenjia Bai, Xuelong Li
  We propose a progressive architecture for humanoid soccer skill acquisition that decomposes learning into motion-skill acquisition, perception-action integration, and sim-to-real transfer. Experiments on the Unitree G1 demonstrate high-fidelity human-like kicking with robust performance under diverse conditions.

Collaboration & Contact

👯 I’m always happy to chat or collaborate on robotics-related projects! Whether it’s robot learning, humanoid control, or any other robotics challenges, feel free to reach out.

📫 Get in Touch:

• Email: kongjp2024@shanghaitech.edu.cn
• WeChat: shakey1972

Looking forward to connecting with you and exploring interesting robotics problems together!