Hi! I am currently a junior undergraduate student at Tsinghua University, majoring in Automation. My primary interests are in robotics, human-robot interaction, and the intersection of control theory and machine learning. At present, I am working on a project integrating diffusion policy with impedance-level control. I am always eager to take on new challenges and collaborate on innovative projects. Currently, I am actively seeking summer research opportunities to further develop my skills and contribute to cutting-edge advancements in these fields.
UltraDP: Generalizable Carotid Ultrasound Scanning with Force-Aware Diffusion Policy
Present UltraDP, a Diffusion-Policy-based method that receives multi-sensory inputs (ultrasound images, wrist camera image, contact wrench, and probe pose) and generates actions that are fit for multi-modal action distributions in autonomous ultrasound scanning. UltraDP achieves a 95% success rate in transverse scanning on previously unseen subjects, demonstrating its effectiveness. Link.
Whole-Body Model Predictive Control for Mobile Manipulation with Task Priority Transition
Developed a Whole-Body Model Predictive Control (WBMPC) framework to manage task priorities and scheduling in multi-task mobile manipulation scenarios. Integrated task priorities into a unified weight matrix, enabling smooth transitions across tasks in both spatial and temporal dimensions. Link.
Planning and Control for Carotid Artery Ultrasound Robots in Clinical Dynamic Environments
Utilized point cloud camera for body tracking and detecting obstacles for motion planning. Applied RRT* algorithm for motion planning and obstacle avoidance using the Franka robotic arm. Integrated human intention recognition for various situations, including human-intended guidance and obstacle avoidance with stable end-effector contact. Coming Soon.
A Path Planning Visualization Tool that includes a companion Franka Robot Controller for Receiving and Executing Trajectories
A path planning visualization tool with state-of-the-art planning algorithms for robot arm planning, with companion Franka joint position/impedance controller for receiving trajectories. View on GitHub.
Typical Food Classification Using AlexNet, ResNet with Grad-CAM
This project focuses on classifying images of 10 popular food categories using a dataset containing 10,000 images. The dataset features diverse food types, including apple pie, chicken wings, dumplings, and more. CNN models based on AlexNet and ResNet18 were evaluated, incorporating data augmentation techniques and a cyclical learning rate to enhance training performance.
