- Smart Agriculture and AI
- Advanced Chemical Sensor Technologies
- Advanced Fluorescence Microscopy Techniques
- Cell Image Analysis Techniques
- Innovative Microfluidic and Catalytic Techniques Innovation
- Horticultural and Viticultural Research
- Leaf Properties and Growth Measurement
- Spectroscopy and Chemometric Analyses
- Advanced Biosensing Techniques and Applications
- Medical Imaging Techniques and Applications
- Microbial Metabolism and Applications
- Gene expression and cancer classification
- Chemistry and Stereochemistry Studies
- Light effects on plants
- Scientific Computing and Data Management
- Research in Cotton Cultivation
- Plant Reproductive Biology
- Mathematical Biology Tumor Growth
- Ovarian cancer diagnosis and treatment
- Viral Infectious Diseases and Gene Expression in Insects
- Optical Polarization and Ellipsometry
- Image Retrieval and Classification Techniques
- Pineapple and bromelain studies
- Tea Polyphenols and Effects
- Computer Graphics and Visualization Techniques
Cornell University
2021-2024
Laboratoire d'Informatique de Paris-Nord
2024
University of Washington
2018-2022
Georgia Institute of Technology
2012-2022
Seattle University
2019
The Wallace H. Coulter Department of Biomedical Engineering
2017
Korea Advanced Institute of Science and Technology
2008-2016
Walt Disney (United States)
2015
Korea Institute of Science and Technology
2010-2011
Korea Institute of Robot and Convergence
2010-2011
Online detection of anomalous execution can be valuable for robot manipulation, enabling robots to operate more safely, determine when a behavior is inappropriate, and otherwise exhibit common sense. By using multiple complementary sensory modalities, could potentially detect wider variety anomalies, such as contact or loud utterance by human. However, task variability the potential false positives make online anomaly challenging, especially long-duration manipulation behaviors. In this...
Partner dance has been shown to be beneficial for the health of older adults. Robots could potentially facilitate healthy aging by engaging adults in partner dance-based exercise. However, involves physical contact between dancers, and would need accepting dancing with a robot. Using methods from technology acceptance literature, we conducted study 16 investigate their robots Participants successfully led human-scale wheeled robot arms (i.e., mobile manipulator) simple, which refer as...
Autonomous feeding is challenging because it requires manipulation of food items with various compliance, sizes, and shapes. To understand how humans manipulate during to explore ways adapt their strategies robots, we collected a rich dataset human trajectories by asking them pick up feed mannequin. From the analysis haptic motion signals, demonstrate that control policies accommodate compliance shape item being acquired. We propose taxonomy for highlight such policies. As first step...
A robot-assisted feeding system can potentially help a user with upper-body mobility impairments eat independently. However, autonomous assistance in the real world is challenging because of varying preferences, impairment constraints, and possibility errors uncertain unstructured environments. An needs to decide appropriate strategy acquire bite hard-to-model deformable food items, right time bring close mouth, transfer easily. Our key insight that should be designed based on user's...
In this paper, we demonstrate data-driven inference of mechanical properties objects using a tactile sensor array (skin) covering robot's forearm. We focus on the mobility (sliding vs. fixed), compliance (soft hard), and identity in environment, as information could be useful for efficient manipulation search. By large surface area forearm, robot potentially search map cluttered volume more efficiently, informed by incidental contact during other tasks. Our approach tracks region forearm...
Physical interactions between two people are ubiquitous in our daily lives, and an integral part of many forms rehabilitation. However, few studies have investigated forces arising from physical humans during a cooperative motor task, particularly overground movements. As such, the direction magnitude interaction human partners, how those used to communicate movement goals, whether they change with experience remains unknown. A better understanding achieved healthy individuals different...
Successful robotic assistive feeding depends on reliable bite acquisition and easy transfer. The latter constitutes a unique type of robot-human handover where the human needs to use mouth. This places high burden robot make transfer easy. We believe that ease not only action but also is tightly coupled with way food item was acquired in first place. To determine factors influencing good transfer, we designed both skewering primitives developed system uses these manipulation feed people...
When making contact with an object, a robot can use tactile sensor consisting of heating element and temperature to recognize the object's material based on conductive heat transfer from object.When this type has time fully reheat prior duration is long enough achieve thermal steady state, numerous methods have been shown perform well.In order enable robots more efficiently sense their environments take advantage brief events over which they lack control, we focus problem recognition given...
Dressing is an important activity of daily living (ADL) with which many people require assistance due to impairments. Robots have the potential provide dressing assistance, but physical interactions between clothing and human body can be complex difficult visually observe. We evidence that data-driven haptic perception used infer relationships during robot-assisted dressing. conducted a carefully controlled experiment 12 participants robot pulled hospital gown along length each person's...
Our long-term goal is to enable a robot engage in partner dance for use rehabilitation therapy, assessment, diagnosis, and scientific investigations of two-person whole-body motor coordination. Partner has been shown improve balance gait people with Parkinson's disease older adults, which motivates our work. During dance, couples rely heavily on haptic interaction convey intent such as speed direction. In this paper, we investigate the potential wheeled mobile human-like upper-body perform...
We present RCareWorld, a human-centric simulation world for physical and social robotic caregiving designed with inputs from stakeholders. RCareWorld has realistic human models of care recipients mobility limitations caregivers, home environments multiple levels accessibility assistive devices, robots commonly used caregiving. It interfaces various physics engines to model diverse material types necessary simulating scenarios, provides the capability plan, control, learn both robot control...
This paper introduces RABBIT, a novel robot-assisted bed bathing system designed to address the growing need for assistive technologies in personal hygiene tasks. It combines multimodal perception and dual (software hardware) compliance perform safe comfortable physical human-robot interaction. Using RGB thermal imaging segment dry, soapy, wet skin regions accurately, RABBIT can effectively execute washing, rinsing, drying tasks line with expert caregiving practices. Our includes...
For millions of adults with mobility limitations, eating meals is a daily challenge. A variety robotic systems have been developed to address this societal need. Unfortunately, end-user adoption robot-assisted feeding limited, in part because existing devices are unable seamlessly grasp, manipulate, and feed diverse foods. Recent works seek issue by creating new algorithms for food acquisition bite transfer. In parallel these algorithmic developments, however, we hypothesize that mechanical...
Bed-to-wheelchair transferring is a ubiquitous activity of daily living (ADL), but especially challenging for caregiving robots with limited payloads. We develop novel algorithm that leverages the presence other assistive devices: Hoyer sling and wheelchair coarse manipulation heavy loads, alongside robot arm fine-grained deformable objects (Hoyer straps). instrument actuators sensors so they can become intelligent agents in algorithm. then focus on one subtask ADL -- tying straps to bar...
Robot caregiving should be personalized to meet the diverse needs of care recipients -- assisting with tasks as needed, while taking user agency in action into account. In physical such handover, bathing, dressing, and rehabilitation, a key aspect this diversity is functional range motion (fROM), which can vary significantly between individuals. work, we learn predict fROM way generalize robot decision-making wide tasks. We propose novel data-driven method for predicting using assessment...
The objective of this observational cohort study was to describe patterns in suckle pressure neonatal dairy heifer calves. Despite technological advancements precision animal health monitoring, morbidity and mortality calves remains pervasive. In experiencing diarrhea, reflex can be measured estimate disease severity by encouraging the calf on a finger. This diagnostic method is highly subjective. To date, physiology not well described sensors measure behavior are available. Our...
Diarrheal and respiratory diseases pose significant threats to pre-weaned dairy calves. Early detection affords prompt intervention, thereby minimizing disease spread severity improving welfare performance. Change in core body temperature can be an early indicator of illness. In calves, this is typically measured via rectal temperature (RT) which time intensive, stressful the calf, invasive. Our study explored potential measuring oral (OT) as alternative fever calves with a goal informing...
Biological organisms benefit from tactile sensing across the entire surfaces of their bodies. Robots may also be able to this type sensing, but fully covering a robot with robust and capable sensors entails numerous challenges. To date, most for robots have been used cover rigid surfaces. In paper, we focus on challenge articulated joints, which requires surface whose geometry varies over time. We first demonstrate importance joints by simulating planar arm reaching in clutter finding...
When operating in human environments, such as homes, robots could use tactile sensing to better perceive objects. A challenge that has not been sufficiently addressed is the influence of an object's surroundings on perception. Prior research focused perception objects laboratory settings. Yet, a number factors found homes can affect multimodal sensing. For example, time-varying thermal characteristics surroundings, sunlight, HVAC, and refrigeration, Likewise, placement object with respect...
Robot-assisted feeding can greatly enhance the lives of those with mobility limitations. Modern systems pick up and position food in front a care recipient's mouth for bite. However, many severe constraints cannot lean forward need direct inside-mouth placement. This demands precision, especially restricted openings, appropriately reacting to various physical interactions - incidental contacts as utensil moves inside, impulsive due sudden muscle spasms, deliberate tongue maneuvers by person...
Surgical teleoperation systems are being increasingly deployed recently. There are, however, some unsolved issues such as nonlinear characteristics of the interaction between slave robot and soft tissues difficulty in employing force sensors surgical end-effectors slave. These make it difficult to generalize any approach develop a control for system. This paper addresses these by proposing <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Robot-assisted feeding (RAF) systems offer enormous potential benefits to community-centered care-giving environments. However, developers of RAF technologies often focus on evaluating their standard transactional functionality, omitting the impact such in contexts that extend past interaction robot and food receiver. have complex social, cultural self-identity implications, since a "meal" extends well beyond simple provisioning nourishment. To better understand these implications we...
This paper focuses on scaled teleoperation systems interacting with soft tissues and presents an optimal control scheme to maximize the operator's kinesthetic perception of remote environments while maintaining stability in macro-micro interactions. Two performance metrics are defined quantify surgeons position tracking ability master-slave system. Kinesthetic is based psychophysics by using two metrics, which relate detection discrimination stimulus. then employs a multiconstrained...
A successful robot-assisted feeding system requires bite acquisition of a wide variety food items. It must adapt to changing user preferences under uncertain visual and physical environments. Different items in different environmental conditions require manipulation strategies for acquisition. Therefore, key challenge is how handle previously unseen with very success rate distributions over strategy. Combining low-level controllers planners into discrete action trajectories, we show that the...