😊 About Me

I am a fourth-year student at the College of Engineering, Peking University, set to graduate with a dual degree in Robotics Engineering and Mechanics. My interests are broad and diverse, and I enjoy communicating with people from all walks of life. As a dedicated football enthusiast, I find joy both in playing the sport and in discussing it with others. I’m always open to academic conversations and welcome any opportunity for discussions or collaborations with like-minded individuals.

I am particularly passionate about applying machine learning methods to elevate robotic capabilities in navigation, perception, and reconstruction tasks. So far, I have contributed to three research projects in these fields, and I look forward to deepening my expertise and broadening my impact in the years to come.

Research Interests

Robotic Navigation

• Efficient Path Planning and Decision Making
• Learning-based Exploration
• Visual SLAM

Autonomous Driving

• 3D Scene Reconstruction
• Perception and Sensor Fusion

🔥 News

• One paper accepted by CVPR 2025.

📝 Publications

CVPR 2025

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes

Chensheng Peng*, Chengwei Zhang*, Yixiao Wang, Chenfeng Xu, Yichen Xie, Wenzhao Zheng, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan

---

-We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction inchallenging driving scenarios.

🎖 Honors and Awards

• 2022 Boeing Scholarship (Third Prize), College of Engineering, Peking University
• 2023 China Optics Valley Scholarship
• 2023 Merit Student of Peking University

📖 Education

2021.09 - 2025.07 (expected), B.S. in Robotics and Mechanics, College of Engineering, Peking University

💻 Research Experiences

2023.05 - 2024.10, Efficient Vision-guided Active SLAM Based on Terrain Information, advised by Prof.Chang Liu, College of Engineering, Peking University.

2024.06 - Now, Reinforcement Learning on Soft Robotics, advised by Prof.Ke Liu, College of Engineering, Peking University.

2024.07 - 2024.11, 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes, advised by Prof.Masayoshi Tomizuka, School of Mechanical Engineering, UC Berkeley.

🛠️ Skills and Tools

• Programming Languages: C, C++, Python, Shell, MATLAB
• Useful Tools: Linux, PyTorch, ROS, LaTeX, Gazebo, Mujoco, SolidWorks