About
Dr. Chenxi Xiao is an Assistant Professor in the School of Information Science and Technology (SIST) at ShanghaiTech University, where he leads the Robot Interaction and Manipulation (RIM) Lab. Prior to joining ShanghaiTech, he received his Ph.D. from Purdue University, where he worked in the Intelligent Systems and Assistive Technologies (ISAT) Laboratory under the supervision of Prof. Juan Wachs.
His research centers on giving robots a rich sense of touch — spanning visuo-tactile sensing, dexterous manipulation, tactile sensors, embodied data collection & synthesis, and teleoperation. He develops autonomous frameworks for efficient tactile exploration and object manipulation, and designs tactile sensors and haptic interfaces that convey physical sensation back to humans.
Research Areas
Themes running through the lab's work.
Tactile Sensing
Developing a broad range of tactile sensors (vision-based, force/pressure, multimodal, and more) to give robots rich touch perception for dexterous manipulation and physical interaction.
Dexterous Manipulation
Creating algorithms and control strategies for multi-fingered robotic hands to perform intricate tasks such as in-hand manipulation and tool use.
Embodied AI & Teleoperation
Building systems for intuitive human-robot teleoperation and collecting high-quality embodied data to train robust robotic policies.
Publications
Selected publications in robotics, tactile sensing, dexterous manipulation, and embodied AI. (Chenxi Xiao highlighted in author lists.)
TriCoSphere: A High-Dexterity, Large-Volume, 3-Finger Coaxial Spherical Manipulator
ICRA (2026)
NLiPsCalib: An Efficient Calibration Framework for High-Fidelity 3D Reconstruction of Curved Visuotactile Sensors
ICRA / arXiv (2026)
Autonomous Exploration for Shape Reconstruction and Measurement via Informative Contact-Guided Planning
IEEE Robotics Autom. Lett. (2026)
HandCraft: Tactile-Informed Hand-Object Dynamics Capture and Realistic Rendering
ACM Multimedia (2025)
R-Tac0: A Rounded High-Frequency Transferable Monochrome Vision-based Tactile Sensor for Shape Reconstruction
IROS (2025)
Touch-Linked Sleeve: A Haptic Interface for Augmented Tactile Perception in Robotic Teleoperation
IROS (2025)
TwinTac: A Wide-Range, Highly Sensitive Tactile Sensor with Real-To-Sim Digital Twin Sensor Model
IROS (2025)
SynPolDex: Synergizing Fingers via Bi-Level Policy Learning for Dexterous Robotic Hands
Humanoids (2025)
Tactile and Chemical Sensing With Haptic Feedback for a Telepresence Explosive Ordnance Disposal Robot
IEEE Trans. Robotics (2023)
Flying Through a Narrow Gap Using End-to-End Deep Reinforcement Learning Augmented With Curriculum Learning and Sim2Real
IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2021)