Research
Research
In-the-Wild Compliant Manipulation with UMI-FT
In-the-Wild Compliant Manipulation with UMI-FT
Hojung Choi*, Yifan Hou*, Chuer Pan, Seongheon Hong, Austin Patel, Xiaomeng Xu, Mark Cutkosky, and Shuran Song
In Review
UMI-FT is a handheld data-collection platform that integrates compact, finger-level force/torque sensors with multimodal vision data to facilitate force-aware policy learning. This system enables the training of adaptive compliance policies that effectively regulate contact forces during complex manipulation tasks, such as wiping or skewering. Ultimately, UMI-FT provides a scalable and cost-effective solution for teaching robots how to perform compliant interactions using real-world demonstrations.
CoinFT: A Coin-Sized 6-Axis Force Torque Sensor for Robotic Applications
CoinFT: A Coin-Sized 6-Axis Force Torque Sensor for Robotic Applications
Hojung Choi*, Jun En Low*, Tae Myung Huh, Gabriela Uribe, Seongheon Hong, Kenneth Hoffmann, Julia Di, Tony Chen, Andrew Stanley, and Mark Cutkosky
In Review
CoinFT is a compact, low-cost, and robust 6-axis force/torque sensor made of stacked PCBs and silicone pillars with comb-shaped electrodes. Its design enables sensitive force measurements while maintaining a small form factor. CoinFT supports diverse contact-rich interactions across platforms like drones, robot end-effectors, and wearable devices. We demonstrate its utility through drone-based force-controlled tasks requiring precise contact modulation.
[Project Website] [arXiv]
Fourigami: A 4-Degree-of-Freedom, Force-Controlled, Origami, Finger Pad Haptic Device
Fourigami: A 4-Degree-of-Freedom, Force-Controlled, Origami, Finger Pad Haptic Device
Crystal E Winsto, Hojung Choi, Rianna Jitosho, Zhenishbek Zhakypov, Jasmin E Palmer, Mark R Cutkosky, and Allison M Okamura
Transactions on Robotics, 2025
Fourigami is a lightweight, 4-DoF haptic device that utilizes origami-inspired manufacturing and pneumatic actuation to provide normal, shear, and twist feedback to the finger pad. By incorporating a 6-DoF force/torque sensor for precise control, the device successfully renders realistic haptic interactions during virtual object manipulation.
[PDF]
DexForce: Extracting Force-Informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation
DexForce: Extracting Force-Informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation
Claire Chen, Zhongchun Yu, Hojung Choi, Mark Cutkosky, and Jeannette Bohg
Robotics and Automation Letters, 2025
We present DexForce, a method for collecting contact-rich dexterous manipulation demonstrations using kinesthetic teaching with force measurements. By incorporating contact forces into action computation, DexForce enables effective imitation learning, achieving a 76% average success rate across six tasks—significantly outperforming force-agnostic baselines, especially in tasks requiring high precision.
[Project Website] [arXiv]
A Damage-perceptive, Self-healing Electronic Skin with Millimeter Resolution
A Damage-perceptive, Self-healing Electronic Skin with Millimeter Resolution
Samuel Root, Can Wu, Hojung Choi, Eric Sun, Gradie Ngaruka, Hyunchang Park, Alexandra Figueroa, Arielle Berman, Diego Patino, Yuran Shi, Carla Pugh, and Zhenan Bao
Device, 2025
We introduce a self-healing electronic skin that mimics human skin’s ability to perceive damage and recover. Using a multilayered architecture and conductive polymers, the skin detects and localizes damage while autonomously healing mechanical and electrical function, offering promise for resilient wearable electronics and robotic sensing.
[PDF]
Additively Manufactured Micro-lattice Dielectrics for Multiaxial Capacitive Sensors
Additively Manufactured Micro-lattice Dielectrics for Multiaxial Capacitive Sensors
Arielle Berman, Kaiwen Hsiao, Samuel E. Root, Hojung Choi, Daniel Ilyn, Chengyi Xu, Emily Stein, Mark Cutkosky, Joseph M. DeSimone, and Zhenan Bao
Science Advances, 2024
The paper presents the development of additively manufactured micro-lattice structures used as dielectric layers in multiaxial capacitive sensors. These sensors, created using continuous liquid interface production (CLIP), exhibit tunable responses under both normal pressure and shear forces, making them suitable for applications in wearable electronics, robotic manipulation, and athletic performance monitoring.
Integrated Pneumatic Sensing and Actuation for Soft Haptic Devices
Integrated Pneumatic Sensing and Actuation for Soft Haptic Devices
Hojung Choi, Mark R Cutkosky, Andrew A Stanley
IEEE Robotics and Automation Letters, 2023
We present an integrated pneumatic sensor and actuator for soft robots and wearable devices that can estimate contact force, location, and shape using a multi-headed neural network. The sensor uses channels cast into a multi-layer silicone bubble that change flow resistance as the bubble deforms, allowing measurements of strain and external contact at the surface.
Deep Learning Classification of Touch Gestures Using Distributed Normal and Shear Force
Deep Learning Classification of Touch Gestures Using Distributed Normal and Shear Force
Hojung Choi, Dane Brouwer, Michael A Lin, Kyle T Yoshida, Carine Rognon, Benjamin Stephens-Fripp, Allison M Okamura, Mark R Cutkosky
IEEE International Conference on Intelligent Robots and Systems (IROS), 2022
Best Poster Presentation Award in IROS Workshop on Large-Scale Robotic Skin: Perception, Interaction, and Control
When humans socially interact with another agent (e.g., human, pet, or robot) through touch, they do so by applying varying amounts of force with different directions, locations, contact areas, and durations. We present a soft, flexible skin with an array of tri-axial tactile sensors for the arm of a person or robot. We demonstrate that shear force information makes a notable difference in touch gesture classification.
Tactile-Informed Action Primitives Mitigate Jamming in Dense Clutter
Tactile-Informed Action Primitives Mitigate Jamming in Dense Clutter
Dane Brouwer, Joshua Citron, Hojung Choi, Marion Lepert, Michael Lin, Jeannette Bohg, Mark Cutkosky
IEEE International Conference on Robotics and Automation (ICRA), 2024, Accepted
It is difficult for robots to retrieve objects in densely cluttered lateral access scenes with movable objects as jamming against adjacent objects and walls can inhibit progress. We propose the use of two action primitives - burrowing and excavating - that can fluidize the scene to unjam obstacles and enable continued progress. We combine the primitives into a closed loop hybrid strategy using tactile and proprioceptive information to leverage the advantages of both primitives without being overly disruptive.
Design and Evaluation of a 3-DoF Haptic Device for Directional Shear Cues on the Forearm
Design and Evaluation of a 3-DoF Haptic Device for Directional Shear Cues on the Forearm
Kyle T Yoshida, Zane A Zook, Hojung Choi, Ming Luo, Marcia K O'Malley, Allison M Okamura
IEEE Transactions on Haptics, 2024, Accepted
Wearable haptic devices on the forearm can relay information from virtual agents, robots, and other humans while leaving the hands free. We introduce and test a new wearable haptic device that uses soft actuators to provide normal and shear force to the skin of the forearm.
Perceived Intensities of Normal and Shear Skin Stimuli Using a Wearable Haptic Bracelet
Perceived Intensities of Normal and Shear Skin Stimuli Using a Wearable Haptic Bracelet
Mine Sarac, Taemyung Huh, Hojung Choi, Mark R Cutkosky, Massimiliano Di Luca, Allison M Okamura
IEEE Robotics and Automation Letters, 2022
We aim to provide effective interaction with virtual objects, despite the lack of co-location of virtual and real-world contacts, while taking advantage of relatively large skin area and ease of mounting on the forearm. We performed two human participant studies to determine the effects of haptic feedback in the normal and shear directions during virtual manipulation using haptic devices worn near the wrist.
Exploratory Hand: Leveraging Safe Contact to Facilitate Manipulation in Cluttered Spaces
Exploratory Hand: Leveraging Safe Contact to Facilitate Manipulation in Cluttered Spaces
Michael A Lin, Rachel Thomasson, Gabriela Uribe, Hojung Choi, Mark Cutkosky
IEEE Robotics and Automation Letters, 2021
We present a new gripper and exploration approach that uses a finger with very low reflected inertia for probing and then grasping objects. The finger employs a transparent transmission, resulting in a light touch when contact occurs.
Dynamically Reconfigurable Tactile Sensor for Robotic Manipulation
Dynamically Reconfigurable Tactile Sensor for Robotic Manipulation
Taemyung Huh, Hojung Choi, Simone Willcox, Stephanie Moon, Mark R Cutkosky
IEEE Robotics and Automation Letters, 2020
We present a tactile sensor intended for manipulation by mobile robots, e.g., in the home. The surface consists of an array of small, rounded bumps or "nibs", which transduce 6-axis force, torque, and slippage into distinguishable capacitance signals. This information can be used for dexterous manipulation tasks such as in-hand object reorientation.
Using Force Data to Self-Pace an Instrumented Treadmill and Measure Self-Selected Walking Speed
Using Force Data to Self-Pace an Instrumented Treadmill and Measure Self-Selected Walking Speed
Seungmoon Song, Hojung Choi, Steve H Collins
Journal of NeuroEngineering and Rehabilitation, 2020
Self-selected speed is an important functional index of walking. A self-pacing controller that reliably matches walking speed using an instrumented treadmill was developed to measure self-selected walking speed.
Jumping Further: Forward Jumps in a Gravity-Reduced Immersive Virtual Environment
Jumping Further: Forward Jumps in a Gravity-Reduced Immersive Virtual Environment
Hyeongyeop Kang, Geonsun Lee, Daeseok Kang, Ohung Kwon, Junyeup Cho, Hojung Choi, Junghyun Han
IEEE Conference on Virtual Reality and 3D User Interfaces (VR), 2019
Best Paper Finalist
In this work, we investigate how to simulate realistic forward jumps in a virtual lunar environment using a cable-driven suspension system.