Xuanbin Peng 彭宣滨
Email: xup004[at]ucsd.edu
Office: Jacobs 4511
I am currently a research assistant at University of California, San Diego (UCSD) advised by Prof. Xiaolong Wang.
My research interest lies in the intersection of robotics, perception, planning, reasoning, and decision-making, with their application in complex, real-world environments.
While immersed in the academic field, I also appreciate letting loose by playing basketball and table tennis during my spare time. Furthermore, philosophy and poetry also interest me a lot.
I remain open and eager to collaborate with like-minded individuals to discover the potential and possibilities of robotics across various fields.
Research
My current research interest lies in data-centric learning, compositionality, mobile manipulation and whole-body control. My long-term goal is to develop general-purpose intelligent robots that can infer and interact with the dynamic and open world environment over long-horizon with adaptability, generalizability, dexterity, and safety.
* denotes equal contribution
Exbody2: Advanced Expressive Humanoid Whole-Body Control
Mazeyu Ji*, Xuanbin Peng*, Fangchen Liu, Ge Yang, Jialong Li, Xuxin Cheng, Xiaolong Wang
A generalized whole-body tracking framework that can take any reference motion inputs and control the humanoid to mimic the motion.
Under Review
WildLMa: Long Horizon Loco-Manipulation in the Wild
Ri-Zhao Qiu*, Yuchen Song*, Xuanbin Peng*, Sai Aneesh Suryadevara, Ge Yang, Minghuan Liu, Mazeyu Ji, Chengzhe Jia, Ruihan Yang, Xueyan Zou, Xiaolong Wang
Integrate an LLM-based high-level planner, an imitation learning skill library, and a learned whole-body controller for in-the-wild loco-manipulation over long-horizon.
Under Review
3D-Spatial Multimodal Memory
Xueyan Zou, Yuchen Song, Ri-zhao Qiu, Xuanbin Peng, Jianglong Ye, Sifei Liu, Xiaolong Wang
Integrate embeddings from foundation models and 3D Gaussian Splatting to restore rich semantic knowledge and 3D-sptial information.
Under Review
RTTF: Rapid Tactile Transfer Framework for Contact-Rich Manipulation Tasks
Qiwei Wu, Xuanbin Peng, Zhouran Sun, Xiaogang Xiong and Yunjiang Lou
Semi-supervised tactile representation learning and sim2real transfer for data efficiency and rapid adaptation across diverse embodiments and tasks.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024.
Accepted, Oral Presentation
Whole-body Compliance Control for Quadruped Manipulator with Actuation Saturation of Joint Torque and Ground Friction
Tianlin Zhang, Xuanbin Peng, Fenghao Lin, Xiaogang Xiong, and Yunjiang Lou
Maintain whole-body compliance control, while mitigating risks associated with torque saturation for safety in human-centric environment.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024.
Accepted, Oral Presentation
Selected Projects
Visual-Inertial SLAM Based on Extended Kalman Filter (EKF)
This project implements a Visual-Inertial SLAM system using stereo-camera and IMU data to estimate both the environment layout and the robot's position. It leverages Extended Kalman Filter (EKF) to fuse IMU-based odometry with visual cues, and uses a Lie-Group manifold for robot pose and landmark joint-updates. A recall buffer optimizes Jacobians matrix computation, achieving accurate, near real-time mapping and localization.
Dynamic Programming for Autonomous Navigation in a Door-Key Environment
This project explores using dynamic programming within a Markov Decision Process framework to navigate an autonomous agent efficiently towards a goal in a Door-Key environment. The system optimally handles doors that may require unlocking with keys located within the environment.
A Versatile Whole-body Mobile Manipulation with Flexible Grasping
The robot won the National Frist Prize in RoboMaster 2022 Robotics Contest.
- Whole-body control for mobile manipulation to fully extend its workspace
- Versatile robot for multi-task skillset, like dragging, fetching and grasping.
- Robust Model-based Autonomous grasping for diverse objects.
Selected Awards and Honors
- National Scholarship. (Ranking 1st-0.3%)2022
- National First Prize in RoboMaster 2022 Robotics Contest.2022
Academic Services
Journal Reviewer:
- IEEE Robotics and Automation Letters (RAL), 2024