Keehoon Kim
Pohang University of Science and Technology · Engineering
About the Lab
Professor Keehoon Kim's research lab specializes in human-machine interaction, focusing on advanced haptic feedback systems for upper extremity prosthetics and rehabilitation. The lab develops innovative haptic devices that deliver multi-modal sensory feedback—such as touch, pressure, shear, and temperature—tailored for targeted reinnervation (TR) patients, enabling more intuitive and precise control of myoelectric prostheses. The lab also applies neural network-based diagnostic systems to complex engineering systems, particularly in nuclear power plant safety, where accurate fault diagnosis and error estimation are critical. Their interdisciplinary work bridges biomechanics, neural engineering, and intelligent control systems to enhance human performance and system reliability.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15In this study, we hypothesized that haptic feedback would enhance grip force control of surface electromyography (sEMG)-controlled prosthetic hands for targeted reinnervation (TR) amputees. A new miniature haptic device, a tactor, that can deliver touch, pressure, shear, and temperature sensation, allows modality-matching haptic feedback. TR surgery that creates sensory regions on the patient's skin that refer to the surface of the missing limb allows somatotopic-matching haptic feedback. This p
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> We have developed three different versions of a multifunction haptic device that can display touch, pressure, vibration, shear force, and temperature to the skin of an upper extremity amputee, especially the one who has undergone targeted nerve reinnervation (TR) surgery. In TR patients, sensation from the reinnervated skin is projected to the missing hand. This paper addresses the design of the mech
The accuracy of the diagnosis obtained from a nuclear power plant fault-diagnostic advisor using neural networks is addressed in this paper in order to ensure the credibility of the diagnosis. A new error estimation scheme called error estimation by series association provides a measure of the accuracy associated with the advisor's diagnoses. This error estimation is performed by a secondary neural network that is fed both the input features for and the outputs of the advisor. Our error estimati
The range of human kinematic motion as well as force resolution should be known for design of a haptic device. In addition, a haptic interface can be designed more easily when master and slave devices are the same kinematically. However, human kinematic factors have not been analyzed and applied deeply because of their complexity. Although calibration techniques have been developed, there is a limit to describe the dexterous motion. In this paper haptic manipulation which uses the tactile sensin
The objective of this research is to develop a fault-diagnostic advisor for nuclear power plant transients that is based on artificial neural networks. A method is described that provides an error bound and therefore a figure of merit for the diagnosis provided by this advisor. The data used in the development of the advisor contain ten simulated anomalies for the San Onofre Nuclear Power Generating Station. The stacked generalization approach is used with two different partitioning schemes. The
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper presents a quantitative comparison framework for bilateral teleoperation systems (BTSs) that have different dynamic characteristics and sensory configurations for a given task-dependent performance objective (TDPO). <formula formulatype="inline"><tex>$\mu$</tex></formula>-synthesis is used to develop the framework since it can efficiently treat systems containing uncertainties and disturba
Estimation of confidence intervals for neural network outputs is important when the uncertainty of a neural network system must be addressed for safety or reliability. This paper presents a new approach for estimating confidence intervals, which can help users validate neural network outputs. The estimation of confidence intervals, called error estimation by series association, is performed by a supplementary neural network trained to predict the error of the main neural network using input feat
Tissue engineering, an interdisciplinary field, aims to restore, maintain, or enhance tissue function by developing biological substitutes. To establish an optimal microenvironment, biofabrication is acknowledged as a revolutionary technology facilitating the construction of multiscale three-dimensional architectures utilising various living cells and biomaterials. A critical challenge in this domain is the precise assembly of soft matter-delicate and pliable tissue structures - essential for cr
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper investigates a novel position-sensor-based force reflection framework for multi-degree-of-freedom (DOF) bilateral teleoperation systems in unstructured environments. The conventional position-sensor-based force reflection method, which is known as position error feedback, may generate grossly inaccurate force reflection directions during collisions involving the slave manipulator links. Th
Design and Analysis of a New 7-DOF Parallel Type Haptic Device : PATHOS-II Keehoon Kim, Wan Kyun Pages 167-172 (2003 Proceedings of the 20th ISARC, Eindhoven, Holland, ISBN 978-90-6814-574-8, ISSN 2413-5844) Abstract: Most tele-operation to manipulate an object consists of gripping and manipulation and two or more 6-DOF haptic devices in master side are usually used. In this article, a new simply designed 7-DOF haptic device, PATHOS II is proposed for 1-DOF gripping and 6-DOF manipulation. The m
In order to provide improved convenience for a surgeon in spinal fusion surgery, a robot system should i) closely engage in surgeon's operation using an end effector, and ii) protect the surgeon from being exposed to harmful radiation due to repeated shootings of fluoroscope. This paper proposes a bilateral teleoperation system for spinal fusion, BiTESS-II, to accomplish the goals. We developed an end effector that can substitute the surgeon's manual operation and a novel closed-loop type slave
A haptic interface can be a passive system with virtual coupling as a filter. Virtual coupling has been designed for satisfying passivity. However, it aects transparency of haptic interface as well as stability. This paper suggests new design criterion of a haptic interface controller by considering transparency. As a result, sampling time and the range of impedance or admittance should be considered as well as virtual coupling for desired performance of haptic display. And experiments show that
This paper proposes restriction space projection (RSP) method to generate accurate direction of force reflection when a bilateral teleoperation system (BTS) is kinematically dissimilar. Through examples, it is shown that the previous force reflection methods are not applicable to the kinematically dissimilar BTSs. Two kinds of RSP methods using a novel concept, instantaneous restriction space (IRS), are implemented for impedance and admittance type of BTSs. Especially, new developed obstacle avo
We have been developing a miniature haptic device -a tactor -that can display pressure, vibration, shear force, and temperature to the skin of upper extremity amputees, especially those who have undergone targeted nerve reinnervation (TRI) surgery. In TRI patients, regions of the reinnervated skin are perceived as being on the phantom hand. This paper presents the mechanical design of the tactor.
Research Areas
Dive deeper into Keehoon Kim's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.