Won Kyung Do

Dr. Won Kyung Do

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 September 2021 in Science Robotics
Verified
Journal Article
Closed access
YLYong Seok Lee
Yong Seok Lee
WDWon Kyung Do
Won Kyung Do
HYHanbyeol Yoon
Hanbyeol Yoon
JHJinuk Heo
Jinuk Heo
WLWonHa Lee
WonHa Lee
DLDongjun Lee
Dongjun Lee
A visual-inertial skeleton tracking framework is presented for accurate, robust, and affordable hand tracking applications.

29 May 2023
Verified
Conference Paper
Open access
WDWon Kyung Do
Won Kyung Do
BJBianca Jurewicz
Bianca Jurewicz
MKMonroe Kennedy
Monroe Kennedy
Collaborative robots stand to have an immense impact on both human welfare in domestic service applications and industrial superiority in advanced manufacturing with dexterous assembly. The outstanding challenge is providing robotic fingertips with a physical design that makes them adept at performing dexterous tasks that require high-resolution, calibrated shape reconstruction and force sensing. In this work, we present DenseTact 2.0, an optical-tactile sensor capable of visualizing the deformed surface of a soft fingertip and using that image in a neural network to perform both calibrated shape reconstruction and 6-axis wrench estimation. We demon-strate the sensor accuracy of 0.3633mm per pixel for shape reconstruction, 0.410N for forces, 0.387N. mm for torques, and the ability to calibrate new fingers through transfer learning, which achieves comparable performance with only 12% of the non-transfer learning dataset size.

17 November 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
WDWon Kyung Do
Won Kyung Do
BABianca Aumann
Bianca Aumann
CCCamille Chungyoun
Camille Chungyoun
MKMonroe Kennedy
Monroe Kennedy
The ability to grasp and manipulate small objects in cluttered environments remains a significant challenge. This letter introduces a novel approach that utilizes a tactile sensor-equipped gripper with eight degrees of freedom to overcome these limitations. We employ DenseTact 2.0 for the gripper, enabling precise control and improved grasp success rates, particularly for small objects ranging from 5 mm to 25 mm. Our integrated strategy incorporates the robot arm, gripper, and sensor to manipulate and orient small objects for subsequent classification, effectively. We contribute a specialized dataset designed for classifying these objects based on tactile sensor output and a new control algorithm for in-hand orientation tasks. Our system demonstrates 88% of successful grasp and successfully classified small objects in cluttered scenarios.

29 March 2024 in SN Computer Science
Verified
Journal Article
Open access
PDF file
JSJose A. Solano-Castellanos
Jose A. Solano-Castellanos
WDWon Kyung Do
Won Kyung Do
MKMonroe D. Kennedy
Monroe D. Kennedy
In this paper, we present a methodology that uses an optical tactile sensor for efficient tactile exploration of embedded objects within soft materials. The methodology consists of an exploration phase, where a probabilistic estimate of the location of the embedded objects is built using a Bayesian approach. The exploration phase is then followed by a mapping phase which exploits the probabilistic map to reconstruct the underlying topography of the workspace by sampling in more detail regions where there are expected to be embedded objects. To demonstrate the effectiveness of the method, we tested our approach on an experimental setup that consists of a series of quartz beads located underneath a polyethylene foam that prevents direct observation of the configuration and requires the use of tactile exploration to recover the location of the beads. We show the performance of our methodology using ten different configurations of the beads where the proposed approach is able to approximate the underlying configuration. We benchmark our results against a random sampling policy. Our empirical results show that our method outperforms the fully random policy in both the exploration and mapping phases. The exploration phase produces a better probabilistic map with fewer samples which enables an earlier transition to the mapping phase to reconstruct the underlying shape. On both the exploration and mapping phases, our proposed method presents a better consistency as compared to the random policy, with smaller standard deviation across the ten different bead configurations.

21 April 2026 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
WDWon Kyung Do
Won Kyung Do
MSMatthew Strong
Matthew Strong
ASAiden Swann
Aiden Swann
BLBoshu Lei
Boshu Lei
MKMonroe Kennedy
Monroe Kennedy
Advanced dexterous manipulation requires identifying and controlling multiple simultaneous contacts, including interactions with compliant objects where deformations are large. Raw optical tactile images are information rich but lack calibrated physical meaning, limiting cross-sensor use and real-world deployment. We present TensorTouch, a calibration framework that combines finite element analysis and learning to infer dense deformation and stress/force fields from a single tactile image. Across real sensors, TensorTouch achieves contact localization errors under 1.29 mm and mean force errors under 0.139 N per axis. In a multi-object selective grasp task with two simultaneously contacted objects (including identical cables), the system achieves up to 90.0% success. We further demonstrate robustness under repeated loading, yielding 38.295 dB PSNR between the initial tactile image and the image after 20,000 contacts. The learned model runs in real time at 95 Hz on an RTX 5090, proving to be suitable for contact-rich, dexterous manipulation.