Chenxi Xiao — RIM Lab, ShanghaiTech University

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.)

NLiPsCalib: An Efficient Calibration Framework for High-Fidelity 3D Reconstruction of Curved Visuotactile Sensors

Xuhao Qin, Feiyu Zhao, Yatao Leng, Runze Hu, Chenxi Xiao

ICRA / arXiv (2026)

About

Research Areas

Tactile Sensing

Dexterous Manipulation

Embodied AI & Teleoperation

Publications

NLiPsCalib: An Efficient Calibration Framework for High-Fidelity 3D Reconstruction of Curved Visuotactile Sensors

DexMove: Learning Tactile-Guided Non-Prehensile Manipulation with Dexterous Hands

TaF-VLA: Tactile-Force Alignment in Vision-Language-Action Models for Force-aware Manipulation

Autonomous Exploration for Shape Reconstruction and Measurement via Informative Contact-Guided Planning

MFE: A Multimodal Hand Exoskeleton With Interactive Force, Pressure and Thermo-Haptic Feedback

PP-Tac: Paper Picking Using Tactile Feedback in Dexterous Robotic Hands

D-LUT: Photorealistic Style Transfer via Diffusion Process

HydroGrasp: A Hydraulic Multi-Fingered Gripper

HandCraft: Tactile-Informed Hand-Object Dynamics Capture and Realistic Rendering

R-Tac0: A Rounded High-Frequency Transferable Monochrome Vision-based Tactile Sensor for Shape Reconstruction

Touch-Linked Sleeve: A Haptic Interface for Augmented Tactile Perception in Robotic Teleoperation

TwinTac: A Wide-Range, Highly Sensitive Tactile Sensor with Real-To-Sim Digital Twin Sensor Model

HumanFT: A Human-Like Fingertip Multimodal Visuo-Tactile Sensor

SynPolDex: Synergizing Fingers via Bi-Level Policy Learning for Dexterous Robotic Hands

Bimanual Grasp Synthesis for Dexterous Robot Hands

Tactile and Chemical Sensing With Haptic Feedback for a Telepresence Explosive Ordnance Disposal Robot

Active Multiobject Exploration and Recognition via Tactile Whiskers

Nonmyopic Informative Path Planning Based on Global Kriging Variance Minimization

Triangle-Net: Towards Robustness in Point Cloud Learning

Flying Through a Narrow Gap Using End-to-End Deep Reinforcement Learning Augmented With Curriculum Learning and Sim2Real