Shaoxiong (Shawn) Wang

I'm a Member of Technical Staff at Tacta. I received my Ph.D. degree from the Computer Science and Artificial Intelligence Laboratory (CSAIL), MIT. I was advised by Edward H. Adelson, and also worked closely with Alberto Rodriguez. During my Ph.D., I worked with Roberto Calandra at Facebook AI Research. I obtained my bachelor's degree from the Department of Computer Science and Technology, Tsinghua University, where I worked with Jie Tang in the Knowledge Engineering Group.

wsxiong [at] gmail (dot) com
CV / Scholar / Github

Industrial Projects

	Dexterous Opening and Closing of an AirPods Case Tacta Systems A contact-rich dexterous manipulation policy trained with reinforcement learning. Touch feedback makes training more efficient, providing contact information that is challenging to obtain from vision alone.
	Tight Packing for Automated Truck Loading Dexterity A transformer-based learned policy tightly packs boxes into slots, closing gaps between boxes to maximize trailer fill. Force feedback enables compliant, contact-rich box handling, detecting contact with walls, floor, and neighboring boxes during placement.

Publications

During my Ph.D., I studied tactile perception & manipulation, computer vision, and machine learning. Some papers are highlighted. * and † indicate equal contribution.

	Tactile-Reactive Roller Grasper Shenli Yuan, Shaoxiong Wang, Radhen Patel, Megha Tippur, Connor Yako, Mark R. Cutkosky, Edward H. Adelson†, Kenneth Salisbury† T-RO, 2025 project page / paper
	DTact: A Vision-Based Tactile Sensor that Measures High-Resolution 3D Geometry Directly from Darkness Changyi Lin, Ziqi Lin, Shaoxiong Wang, Huazhe Xu ICRA, 2023 project page / arXiv
	Visuotactile Affordances for Cloth Manipulation with Local Control Neha Sunil, Shaoxiong Wang, Yu She, Edward H. Adelson, Alberto Rodriguez CoRL, 2022 project page / arXiv
	See, Hear, Feel: Smart Sensory Fusion for Robotic Manipulation Hao Li, Yizhi Zhang, Junzhe Zhu, Shaoxiong Wang, Michelle A. Lee, Huazhe Xu, Edward H. Adelson, Li Fei-Fei, Ruohan Gao†, Jiajun Wu† CoRL, 2022 project page / arXiv
	Towards Learning to Play Piano with Dexterous Hands and Touch Huazhe Xu, Yuping Luo, Shaoxiong Wang, Trevor Darrell, Roberto Calandra IROS, 2022 arXiv
	TACTO: A Fast, Flexible, and Open-Source Simulator for High-Resolution Vision-Based Tactile Sensors Shaoxiong Wang, Michael Lambeta, Po-Wei Chou, Roberto Calandra RA-L & ICRA, 2022 (NeurIPS 2020 Workshops: Robot Learning; Deep Reinforcement Learning) code / arXiv
	GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Finger Shaoxiong Wang, Yu She, Branden Romero, Edward H. Adelson ICRA, 2021 project page / arXiv
	PyTouch: A Machine Learning Library for Touch Processing Michael Lambeta, Huazhe Xu, Jingwei Xu, Po-Wei Chou, Shaoxiong Wang, Trevor Darrell, Roberto Calandra ICRA, 2021 code / arXiv
	SwingBot: Learning Physical Features from In-Hand Tactile Exploration for Dynamic Swing-up Manipulation Chen Wang, Shaoxiong Wang, Branden Romero, Filipe Veiga, Edward H. Adelson IROS, 2020 (Best Paper Award) project page / paper / MIT CSAIL news
	Cable Manipulation with a Tactile-Reactive Gripper Yu She, Shaoxiong Wang, Siyuan Dong, Neha Sunil, Alberto Rodriguez, Edward H. Adelson RSS, 2020 (Best Paper Award Finalist) IJRR*, 2021 project page / arXiv / MIT News
	3D Shape Perception from Monocular Vision, Touch, and Shape Priors Shaoxiong Wang, Jiajun Wu, Xingyuan Sun, Wenzhen Yuan, William T. Freeman, Joshua B. Tenenbaum, Edward H. Adelson IROS, 2018 project page / arXiv
	Active Clothing Material Perception using Tactile Sensing and Machine Learning Wenzhen Yuan, Yuchen Mo, Shaoxiong Wang, Edward H. Adelson ICRA, 2018 project page / arXiv / data
	Connecting Look and Feel: Associating the Visual and Tactile Properties of Physical Materials Wenzhen Yuan, Shaoxiong Wang, Siyuan Dong, Edward H. Adelson CVPR, 2017 (Oral) project page / paper / data
	Active Zero-Shot Learning Sihong Xie, Shaoxiong Wang, Philip S. Yu CIKM, 2016 paper / data

Side Projects

	MIT 6.943[J] How To Make (Almost) Anything video / website Teleoperation with force feedback: an ATmega16U4 micro-controller with USB support via the LUFA library, Hall-effect sensors & magnets for force sensing, and a 3D-printed cable-driven robot hand (Yale OpenHand).
	Music Generation with Long Short-Term Memory 1st Place in Microsoft Campus Elite Program (news) Grand Prize in 35th Tsinghua Challenge Cup, top 6 among 381 teams (news) A comprehensive music generation system based on Long Short-Term Memory (LSTM) networks. It generates music automatically driven by data and is embedded with rich music knowledge.

Website template from Jon Barron.