Person:

Kemp, Charles C.

Permanent Link

https://hdl.handle.net/1853/72201

Associated Organization(s)

Organizational Unit

Wallace H. Coulter Department of Biomedical Engineering

Full item page

Publication Search Results

Now showing 1 - 10 of 51

Haptic Simulation for Robot-Assisted Dressing

(Georgia Institute of Technology, 2017) Yu, Wenhao ; Kapusta, Ariel ; Tan, Jie ; Kemp, Charles C. ; Turk, Greg ; Liu, C. Karen

There is a considerable need for assistive dressing among people with disabilities, and robots have the potential to fulfill this need. However, training such a robot would require extensive trials in order to learn the skills of assistive dressing. Such training would be time-consuming and require considerable effort to recruit participants and conduct trials. In addition, for some cases that might cause injury to the person being dressed, it is impractical and unethical to perform such trials. In this work, we focus on a representative dressing task of pulling the sleeve of a hospital gown onto a person’s arm. We present a system that learns a haptic classifier for the outcome of the task given few (2-3) real-world trials with one person. Our system first optimizes the parameters of a physics simulator using real-world data. Using the optimized simulator, the system then simulates more haptic sensory data with noise models that account for randomness in the experiment. We then train hidden Markov Models (HMMs) on the simulated haptic data. The trained HMMs can then be used to classify and predict the outcome of the assistive dressing task based on haptic signals measured by a real robot’s end effector. This system achieves 92.83% accuracy in classifying the outcome of the robot-assisted dressing task with people not included in simulation optimization. We compare our classifiers to those trained on real-world data. We show that the classifiers from our system can categorize the dressing task outcomes more accurately than classifiers trained on ten times more real data.
Data-Driven Haptic Perception for Robot-Assisted Dressing

(Georgia Institute of Technology, 2016-08) Kapusta, Ariel ; Yu, Wenhao ; Bhattacharjee, Tapomayukh ; Liu, C. Karen ; Turk, Greg ; Kemp, Charles C.

Dressing is an important activity of daily living (ADL) with which many people require assistance due to impairments. Robots have the potential to provide dressing assistance, but physical interactions between clothing and the human body can be complex and difficult to visually observe. We provide evidence that data-driven haptic perception can be used to infer relationships between clothing and the human body during robot-assisted dressing. We conducted a carefully controlled experiment with 12 human participants during which a robot pulled a hospital gown along the length of each person’s forearm 30 times. This representative task resulted in one of the following three outcomes: the hand missed the opening to the sleeve; the hand or forearm became caught on the sleeve; or the full forearm successfully entered the sleeve. We found that hidden Markov models (HMMs) using only forces measured at the robot’s end effector classified these outcomes with high accuracy. The HMMs’ performance generalized well to participants (98.61% accuracy) and velocities (98.61% accuracy) outside of the training data. They also performed well when we limited the force applied by the robot (95.8% accuracy with a 2N threshold), and could predict the outcome early in the process. Despite the lightweight hospital gown, HMMs that used forces in the direction of gravity substantially outperformed those that did not. The best performing HMMs used forces in the direction of motion and the direction of gravity.
Collaboration Between a Robotic Bed and a Mobile Manipulator May Improve Physical Assistance for People with Disabilities

(Georgia Institute of Technology, 2016-08) Kapusta, Ariel ; Chitalia, Yash ; Park, Daehyung ; Kemp, Charles C.

We present a robotic system designed to provide physical assistance to a person in bed. The system consists of a robotic bed (Autobed) and a mobile manipulator (PR2) that work together. The 3 degree-of-freedom (DoF) robotic bed moves the person’s body and uses a pressure sensing mat to estimate the body’s position. The mobile manipulator positions itself with respect to the bed and compliantly moves a lightweight object with one of its 7-DoF arms. The system optimizes its motions with respect to a task model and a model of the human’s body. The user provides high-level supervision to the system via a web-based interface. We first evaluated the ability of the robotic bed to estimate the location of the head of a person in a supine configuration via a study with 7 able-bodied participants. This estimation was robust to bedding, including a pillow under the person’s head. We then evaluated the ability of the full system to autonomously reach task-relevant poses on a medical mannequin placed in a supine position on the bed. We found that the robotic bed’s motion and perception each improved the overall system’s performance. Our results suggest that this type of multi-robot system could more effectively bring objects to desired locations with respect to the user’s body than a mobile manipulator working alone. This may in turn lead to improved physical assistance for people with disabilities at home and in healthcare facilities, since many assistive tasks involve an object being moved with respect to a person’s body.
Multimodal Execution Monitoring for Anomaly Detection During Robot Manipulation

(Georgia Institute of Technology, 2016-05) Park, Daehyung ; Erickson, Zackory ; Bhattacharjee, Tapomayukh ; Kemp, Charles C.

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 more common sense. By using multiple complementary sensory modalities, robots could potentially detect a wider variety of anomalies, such as anomalous contact or a loud utterance by a human. However, task variability and the potential for false positives make online anomaly detection challenging, especially for long-duration manipulation behaviors. In this paper, we provide evidence for the value of multimodal execution monitoring and the use of a detection threshold that varies based on the progress of execution. Using a data-driven approach, we train an execution monitor that runs in parallel to a manipulation behavior. Like previous methods for anomaly detection, our method trains a hidden Markov model (HMM) using multimodal observations from non-anomalous executions. In contrast to prior work, our system also uses a detection threshold that changes based on the execution progress. We evaluated our approach with haptic, visual, auditory, and kinematic sensing during a variety of manipulation tasks performed by a PR2 robot. The tasks included pushing doors closed, operating switches, and assisting ablebodied participants with eating yogurt. In our evaluations, our anomaly detection method performed substantially better with multimodal monitoring than single modality monitoring. It also resulted in more desirable ROC curves when compared with other detection threshold methods from the literature, obtaining higher true positive rates for comparable false positive rates.
Towards Assistive Feeding with a General-Purpose Mobile Manipulator

(Georgia Institute of Technology, 2016-05) Park, Daehyung ; Kim, You Keun ; Erickson, Zackory ; Kemp, Charles C.

General-purpose mobile manipulators have the potential to serve as a versatile form of assistive technology. However, their complexity creates challenges, including the risk of being too difficult to use. We present a proof-of-concept robotic system for assistive feeding that consists of a Willow Garage PR2, a high-level web-based interface, and specialized autonomous behaviors for scooping and feeding yogurt. As a step towards use by people with disabilities, we evaluated our system with 5 able-bodied participants. All 5 successfully ate yogurt using the system and reported high rates of success for the system’s autonomous behaviors. Also, Henry Evans, a person with severe quadriplegia, operated the system remotely to feed an able-bodied person. In general, people who operated the system reported that it was easy to use, including Henry. The feeding system also incorporates corrective actions designed to be triggered either autonomously or by the user. In an offline evaluation using data collected with the feeding system, a new version of our multimodal anomaly detection system outperformed prior versions.
Autobed: A Web-Controlled Robotic Bed

(Georgia Institute of Technology, 2016-02) Grice, Phillip M. ; Chitalia, Yash ; Rich, Megan ; Clever, Henry ; Evans, Henry ; Evans, Jane ; Kemp, Charles C.

We (the Healthcare Robotics Lab at Georgia Tech) have developed an additional module for an Invacare fully electric hospital bed (Model 5410IVC) so that the bed can be controlled from a web-based interface. This module can be easily plugged between the hand control and the Invacare bed, without having to modify any existing hardware on the bed. We call a bed so modified an 'Autobed.' With this feature, users who are unable to operate the standard bed controls, but can access a web browser, are able to position the bed by themselves without having to rely on a caregiver (for example, patients with quadriplegia). This page describes how to make the Autobed module using relatively inexpensive, commercially available hardware. This document is a representation of the content provided at http://hsi.gatech.edu/hrl/project_autobed_v2.shtml as of February 15th, 2016, and is intended to create a lasting, citable, and archival copy of this material, which details the design and instructions for building the 'Autobed' device.
Optimization of Robot Configurations for Assistive Tasks

(Georgia Institute of Technology, 2016) Kapusta, Ariel ; Kemp, Charles C.

Robots can provide assistance with activities of daily living (ADLs) to humans with motor impairments. Specialized robots, such as desktop robotic feeding systems, have been successful for specific assistive tasks when placed in fixed and designated positions with respect to the user. General-purpose mobile manipulators could act as a more versatile form of assistive technology, able to perform many tasks, but selecting a configuration for the robots from which to perform a task can be challenging due to the high number of degrees of freedom of the robots and the complexity of the tasks. As with the specialized, fixed robots, once in a good configuration, another system or the user can provide the fine control to perform the details of the task. In this short paper, we present Task-centric Optimization of robot Configurations (TOC), a method for selecting configurations for a PR2 and a robotic bed to allow the PR2 to provide effective assistance with ADLs. TOC builds upon previous work, Task-centric initial Configuration Selection (TCS), addressing some of the limitations of TCS. Notable alterations are selecting configurations from the continuous configuration space using a Covariance Matrix Adaptation Evolution Strategy (CMA-ES) optimization, introducing a joint-limit-weighted manipulability term, and changing the framework to move all optimization offline and using function approximation at run-time. To evaluate TOC, we created models of 13 activities of daily living (ADLs) and compared TOC’s and TCS’s performance with these 13 assistive tasks in a computer simulation of a PR2, a robotic bed, and a model of a human body. TOC performed as well or better than TCS in most of our tests against state estimation error. We also implemented TOC on a real PR2 and a real robotic bed and found that from the TOC-selected configuration the PR2 could reach all task-relevant goals on a mannequin on the bed.
Autobed: Open Hardware for Accessible Web-based Control of an Electric Bed

(Georgia Institute of Technology, 2016) Grice, Phillip M. ; Chitalia, Yash ; Rich, Megan ; Clever, Henry M. ; Kemp, Charles C.

Individuals with severe motor impairments often have difficulty operating the standard controls of electric beds and so require a caregiver to adjust their position for utility, comfort, or to prevent pressure ulcers. Assistive human-computer interaction devices allow many such individuals to operate a computer and web browser. Here, we present the Autobed, a Wi-Fi-connected device that enables control of an Invacare Full-Electric Homecare Bed, a Medicare-approved device in the US, from any modern web browser, without modification of existing hardware. We detail the design and operation of the Autobed. We also examine its usage by one individual with severe motor impairments and his primary caregiver in their own home, including usage logs from a period of 102 days and detailed questionnaires. Finally, we make the entire system, including hardware design and components, software, and build instructions, available under permissive open-source licenses.
A Model that Predicts the Material Recognition Performance of Thermal Tactile Sensing

( 2016) Bhattacharjee, Tapomayukh ; Bai, Haoping ; Chen, Haofeng ; Kemp, Charles C.

Tactile sensing can enable a robot to infer properties of its surroundings, such as the material of an object. Heat transfer based sensing can be used for material recognition due to differences in the thermal properties of materials. While datadriven methods have shown promise for this recognition problem, many factors can influence performance, including sensor noise, the initial temperatures of the sensor and the object, the thermal effusivities of the materials, and the duration of contact. We present a physics-based mathematical model that predicts material recognition performance given these factors. Our model uses semi-infinite solids and a statistical method to calculate an F1 score for the binary material recognition. We evaluated our method using simulated contact with 69 materials and data collected by a real robot with 12 materials. Our model predicted the material recognition performance of support vector machine (SVM) with 96% accuracy for the simulated data, with 92% accuracy for real-world data with constant initial sensor temperatures, and with 91% accuracy for real-world data with varied initial sensor temperatures. Using our model, we also provide insight into the roles of various factors on recognition performance, such as the temperature difference between the sensor and the object. Overall, our results suggest that our model could be used to help design better thermal sensors for robots and enable robots to use them more effectively.
Nonhuman Present: Science and Fiction

( 2015-10-30) Khapaeva, Dina ; Senf, Carol ; Kemp, Charles C. ; Chernoff, Yury O. ; Yaszek, Lisa