Novel 3D Vision and Touch Sensing for Autonomous and Flexible Robot PCB Assembly

Interdisciplinary Areas: Data and Engineering Applications, Autonomous and Connected Systems, Future Manufacturing

Project Description

Printed Circuit Board (PCB) has a high demand and has a market size of $57.5 billion in 2020 and $69.5B by 2024. However, most PCBs are assembled by human hands, which is increasingly difficult due to component miniaturization and increased density of PCBs as well as quickly rising human labor cost. Robot PCB assembly offers a promising alternative solution but has grand challenges, such as (i) how to develop dexterous robotic grippers that can manipulate deformable solder wires and DuPont lines for soldering and harnessing, while most commercial robotic hands are designed to manipulate rigid objects? (ii) how to effectively estimate the pose of assembly tools within the robotic hand when tools are easily occluded from vision? (iii) how to localize sub-millimeter electronic features/components quickly and precisely in 3D space when commercial 3D vision sensors have limited spatial and/or temporal resolutions? and (iv) how to feed sensing data into the control loop to modulate the grasp pose and grip force on the fly when data analytics is computational inefficiency? We propose to tackle these challenges in PCB assembly by creating novel tactile-reactive robotic hands, innovating 3D vision and touch sensing techniques, and developing computationally efficient control/planning algorithms.

Start Date

Spring/Summer 2022

Postdoctoral Qualifications

• Solid backgrounds in robotics, tactile sensing, computer vision, mechanism design;
• Passion and interest to solve challenging research problems using methodologies from different areas;
• Good communication and writing skills;
• Ability to thrive in a collaborative environment.


Yu She
Assistant Professor
School of Industrial Engineering
Purdue University

Song Zhang
School of Mechanical Engineering
Purdue University


[1] Yu She, Shaoxiong Wang, Siyuan Dong, Neha Sunil, Alberto Rodriguez and Edward Adelson, “Cable Manipulation with a Tactile-Reactive Gripper.” International Journal of Robotics Research, August 2021. doi:10.1177/02783649211027233
[2] Shaoxiong Wang, Yu She, Brandon Romero, and Edward Adelson, “GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Finger.” IEEE International Conference on Robotics and Automation (ICRA), Xian, China, May 30 – June 5, 2021.
[3] Yu She, Sandra Q. Liu, Peiyu Yu, and Edward Adelson. "Exoskeleton-covered soft finger with vision-based proprioception and tactile sensing." In 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 10075-10081. IEEE, 2020.
[4] Tyler Bell, Bogdan Vlahov, Jan P. Allebach, and Song Zhang, "Three-dimensional range geometry compression via phase encoding," Appl. Opt., 56(33), 9285-9292, (2017); doi: 10.1364/AO.56.009285
[5] Xiaowei Hu, Song Zhang, Yujin Zhang, Yongpan Liu, and Guijin Wang. "Large depth-of-field three-dimensional shape measurement with the focal sweep technique." Optics Express 28, no. 21 (2020): 31197-31208.