Charlie Kemps 2008 Robotics Institute Seminar at CMU Healthcare Robotics Lab 2025-04-24 | Autonomous Mobile Manipulation for the Motor ImpairedCharlie KempGeorgia TechTime and PlaceMauldin Auditorium (NSH 1305)Time: 3:30pm to 4:30pm on October 31, 2008https://www.cs.cmu.edu/~robocast/https://www.cs.cmu.edu/~ri-seminar/2008.fall/2008-10-31.htmlAbstractFor millions of people on a daily basis, motor impairments diminish quality of life, reduce independence, and increase healthcare costs. Assistive robots that autonomously manipulate objects within everyday settings offer the potential to improve the lives of the elderly, injured, and disabled by augmenting their abilities with those of a cooperative robot. Within this talk, I will give an overview of my lab's research on autonomous mobile manipulation for people with motor impairments, which has resulted in EL-E, a prototype mobile manipulator capable of performing a variety of assistive manipulation tasks, such as object fetching, door opening, and drawer opening.Three key questions drive this research: what tasks would be valuable for an assistive robot to perform; how can motor-impaired users direct a robot to perform these tasks; and how can a robot perform these tasks in unstructured environments, such as the home? To help answer these questions, we have taken inspiration from helper monkeys and service dogs. We have also integrated patient studies throughout the research process from initial design to systems-level evaluation through our collaboration with the ALS Center at the Emory School of Medicine. By taking a problem-driven, systems-level approach to our research, we have found synergistic answers to these questions that enable patients to work with robots in complementary ways that circumvent common stumbling blocks to deployable, real-world solutions.Speaker BiographyCharles C. Kemp is an Assistant Professor in the Department of Biomedical Engineering at Georgia Tech and Emory University. He received a doctorate in Electrical Engineering and Computer Science from MIT in 2005. He is a member of the Center for Robotics and Intelligent Machines at Georgia Tech and the Health Systems Institute, which houses his lab (http://healthcare-robotics.com). Charlie's current research focuses on autonomous robot manipulation and human-robot interaction for healthcare (http://charliekemp.com).
ICRA 2022 Presentation: The Design of Stretch Healthcare Robotics Lab 2022-04-07 | This is a 4-minute-long conference presentation for our ICRA 2022 paper on the design of the Stretch mobile manipulator [1]. Prof. Charlie Kemp provides the voice over. Link to the paper on arXiv: arxiv.org/abs/2109.10892Link to the Google Slides: docs.google.com/presentation/d/102LSy5qFg8MYLlgUIkJc7S2uzXbjEZ-PlcuK_4ZErZ4[1] The Design of Stretch: A Compact, Lightweight Mobile Manipulator for Indoor Human Environments, Charles C. Kemp, Aaron Edsinger, Henry M. Clever and Blaine Matulevich, IEEE International Conference on Robotics and Automation (ICRA), 2022. Conflict of Interest Statement: In addition to being an associate professor at Georgia Tech, Charlie Kemp is a co-founder and the chief technology officer (CTO) of Hello Robot Inc. where he works part time. He owns equity in Hello Robot Inc. and is an inventor of Georgia Tech intellectual property (IP) licensed by Hello Robot Inc. Consequently, he receives royalties through Georgia Tech for sales made by Hello Robot Inc. He also benefits from increases in the value of Hello Robot Inc.
Stretch with Stretch: Robot-led Physical Therapy for Individuals with Parkinsons Disease Healthcare Robotics Lab 2022-03-30 | This is the final project video for Stretch with Stretch. It was produced by Team Blue in the Fall of 2021 for a project-based class at Georgia Tech named Robotic Caregivers taught by Prof. Charlie Kemp. The members of Team Blue were Madeline Beatty, Matthew Lamsey, Zexuan Liu, Arjun Majumdar, and Kendra Washington. The class website can be found via the following link: https://sites.gatech.edu/robotic-caregivers/Conflict of Interest Statement: This class was taught by Prof. Charlie Kemp. The class uses the Stretch RE1 robot from Hello Robot Inc. In addition to being an associate professor at Georgia Tech, Prof. Charlie Kemp is a co-founder and the chief technology officer (CTO) of Hello Robot Inc. where he works part time. He owns equity in Hello Robot and is an inventor of Georgia Tech intellectual property (IP) licensed by Hello Robot. Consequently, he receives royalties through Georgia Tech for sales made by Hello Robot. He also benefits from increases in the value of Hello Robot.
The Bottle Butler by Team Red - Final Project for Robotic Caregivers Healthcare Robotics Lab 2021-12-09 | This is the final project video for the Bottle Butler. It was produced by Team Red in the Fall of 2021 for a project-based class at Georgia Tech named Robotic Caregivers.The class website can be found via the following link: https://sites.gatech.edu/robotic-caregivers/Conflict of Interest Statement: This class was taught by Prof. Charlie Kemp. The class uses the Stretch RE1 robot from Hello Robot Inc. In addition to being an associate professor at Georgia Tech, Prof. Charlie Kemp is a co-founder and the chief technology officer (CTO) of Hello Robot Inc. where he works part time. He owns equity in Hello Robot and is an inventor of Georgia Tech intellectual property (IP) licensed by Hello Robot. Consequently, he receives royalties through Georgia Tech for sales made by Hello Robot. He also benefits from increases in the value of Hello Robot.
Mobile Cobots as Assistive Technology by Prof. Charlie Kemp Healthcare Robotics Lab 2021-03-03 | A course lecture by Prof. Charlie Kemp covering research from the Healthcare Robotics Lab at Georgia Tech since 2007. ______________________Course InformationRobotic Caregivers: From Dreams to Reality (Spring 2021)BMED 4833/8813 at Georgia Tech in Atlanta, GeorgiaLectures: Tuesday/Thursday 12:30pm to 1:45pm ETInstructors: Zackory Erickson and Prof. Charlie KempOverviewRobotics researchers and futurists have long dreamed of robots that can serve as caregivers. In this hands-on project-based course, you will learn about future opportunities and present realities for autonomous robots that serve as caregivers. You will also gain experience with key technologies for the creation of autonomous robots, including physics simulation, perception, action, human-robot interaction, and learning.
Evaluating Assistive Devices by Henry Evans Healthcare Robotics Lab 2021-01-26 | On January 26, 2021, Henry Evans gave this talk to the Georgia Tech class Robotic Caregivers: From Dreams to Reality.
Robotic Caregivers Class 2021 - Lecture 2 Healthcare Robotics Lab 2021-01-20 | Excerpts from Zackory Erickson lecture on Assistive Gym for Robotic Caregivers: From Dreams to Reality.----------------------Course InformationRobotic Caregivers: From Dreams to Reality (Spring 2021)BMED 4833/8813 at Georgia Tech in Atlanta, GeorgiaLectures: Tuesday/Thursday 12:30pm to 1:45pm ETInstructors: Zackory Erickson and Prof. Charlie KempOverviewRobotics researchers and futurists have long dreamed of robots that can serve as caregivers. In this hands-on project-based course, you will learn about future opportunities and present realities for autonomous robots that serve as caregivers. You will also gain experience with key technologies for the creation of autonomous robots, including physics simulation, perception, action, human-robot interaction, and learning.
Robotic Caregivers Class 2021 - Lecture 1 Healthcare Robotics Lab 2021-01-16 | Excerpts from Prof. Charlie Kemp's first lecture for Robotic Caregivers: From Dreams to Reality.Correction: Prof. Kemp meant to refer to the Pirates of the Caribbean ride at Disneyland rather than The Pirates of Penzance comic opera!----------------------Course InformationRobotic Caregivers: From Dreams to Reality (Spring 2021)BMED 4833/8813 at Georgia Tech in Atlanta, GeorgiaLectures: Tuesday/Thursday 12:30pm to 1:45pm ETInstructors: Zackory Erickson and Prof. Charlie KempOverviewRobotics researchers and futurists have long dreamed of robots that can serve as caregivers. In this hands-on project-based course, you will learn about future opportunities and present realities for autonomous robots that serve as caregivers. You will also gain experience with key technologies for the creation of autonomous robots, including physics simulation, perception, action, human-robot interaction, and learning.
NewRo goes to a real home to learn what things feel like Healthcare Robotics Lab 2020-07-14 | NewRo, the patent pending Georgia Tech prototype that led to Stretch, went to a real home to learn what things feel like. NewRo touched a variety of objects using a multimodal tactile sensor. The results of this research were published in the following paper:Multimodal Tactile Perception of Objects in a Real Home, Tapomayukh Bhattacharjee, Henry M. Clever, Joshua Wade, and Charles C. Kemp, IEEE Robotics and Automation Letters (RA-L) , 2018.http://pwp.gatech.edu/hrl/wp-content/uploads/sites/231/2019/08/Multimodal_Tactile_Perception.pdfConflict of Interest Statement: Dr. Charles C. Kemp owns equity in and works for Hello Robot Inc., a company that has commercialized robotic assistance technologies initially developed in the Healthcare Robotics Lab at Georgia Tech. Henry M. Clever is entitled to royalties derived from Hello Robot’s sale of products.
NewRo : The Georgia Tech prototype that led to Stretch Healthcare Robotics Lab 2020-07-14 | Starting in October of 2016, Prof. Charlie Kemp and Henry M. Clever invented a new kind of robot. They named the prototype NewRo. In March of 2017, Prof. Kemp filmed this video of Henry operating NewRo to perform a number of assistive tasks. While visiting the Bay Area for a AAAI Symposium workshop at Stanford, Prof. Kemp showed this video to a select group of people to get advice, including Dr. Aaron Edsinger. In August of 2017, Dr. Edsinger and Dr. Kemp founded Hello Robot Inc. to commercialize this patent pending assistive technology. Hello Robot Inc. licensed the intellectual property (IP) from Georgia Tech. After three years of stealthy effort, Hello Robot Inc. revealed Stretch, a new kind of robot!Conflict of Interest Statement: Dr. Kemp owns equity in and works for Hello Robot Inc., a company that has commercialized robotic assistance technologies initially developed in the Healthcare Robotics Lab at Georgia Tech. Henry M. Clever is entitled to royalties derived from Hello Robot’s sale of products.
Multimodal Material Classification for Robots using Spectroscopy and High Resolution Texture Imaging Healthcare Robotics Lab 2020-07-01 | Accompanying video for the paper:Zackory Erickson, Eliot Xing, Bharat Srirangam, Sonia Chernova, and Charles C. Kemp, "Multimodal Material Classification for Robots using Spectroscopy and High Resolution Texture Imaging", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020.
Bodies at Rest: 3D Human Pose and Shape Estimation From a Pressure Image Using Synthetic Data Healthcare Robotics Lab 2020-06-29 | Accompanying video for the paper:Henry M. Clever, Zackory Erickson, Ariel Kapusta, Greg Turk, Karen Liu, Charles C. Kemp; The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 6215-6224
Assistive VR Gym: Using Interactions with Real People to Improve Virtual Assistive Robots Healthcare Robotics Lab 2020-06-29 | Accompanying video for the paper:Z. Erickson*, Y. Gu*, and C. C. Kemp, “Assistive VR Gym: Using Interactions with Real People to Improve Virtual Assistive Robots”, IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 2020.
Personalized Collaborative Plans for Robot-Assisted Dressing via Optimization and Simulation Healthcare Robotics Lab 2020-06-29 | Accompanying video for the paper:A. Kapusta, Z. Erickson, H. M. Clever, W. Yu, C. K. Liu, G. Turk, and C. C. Kemp, “Personalized Collaborative Plans for Robot-Assisted Dressing via Optimization and Simulation,” Autonomous Robots (AURO), 2019.
Assistive Gym: A Physics Simulation Framework for Assistive Robotics Healthcare Robotics Lab 2020-06-01 | Accompanying video for the paper:Zackory Erickson, Vamsee Gangaram, Ariel Kapusta, C. Karen Liu, and Charles C. Kemp, “Assistive Gym: A Physics Simulation Framework for Assistive Robotics”, IEEE International Conference on Robotics and Automation (ICRA), 2020.
Active Robot-Assisted Feeding with a General-Purpose Mobile Manipulator Healthcare Robotics Lab 2019-05-18 | Accompanying video for the paper:D. Park, Y. Hoshi, H. P. Mahajan, H. K. Kim, Z. Erickson, W. A. Rogers, C. C. Kemp, “Active Robot- Assisted Feeding with a General-Purpose Mobile Manipulator: Design, Evaluation, and Lessons Learned,” Robotics and Autonomous Systems, 2020.
Multidimensional Capacitive Sensing for Robot-Assisted Dressing and Bathing Healthcare Robotics Lab 2019-05-18 | Z. Erickson, H. M. Clever, V. Gangaram, G. Turk, C. K. Liu, and C. C. Kemp, “Multidimensional Capacitive Sensing for Robot-Assisted Dressing and Bathing”, International Conference on Rehabilitation Robotics (ICORR), 2019. (Finalist for Best Student Paper)
Classification of Household Materials via Spectroscopy Healthcare Robotics Lab 2019-05-18 | Z. Erickson, N. Luskey, S. Chernova, and C. C. Kemp, “Classification of Household Materials via Spectroscopy”, IEEE Robotics and Automation Letters (RA-L), 2019. (presented at ICRA 2019) (Finalist for Best Paper Award in Service Robotics at IEEE Conference on Robotics and Automation (ICRA 2019))
Autonomous Grasping of Tools from Portable Toolbox via ARTags (uploaded Feb 8, 2012) Healthcare Robotics Lab 2019-04-03 | ...
Lead me by the hand: Evaluation of a direct physical interface for nursing assistant robots Healthcare Robotics Lab 2019-04-03 | Chen, Tiffany L., and Charles C. Kemp. "Lead me by the hand: Evaluation of a direct physical interface for nursing assistant robots." In 2010 5th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 367-374. IEEE, 2010.
Teleoperated exploration of a canvas bag using tactile sensing and model predictive control Healthcare Robotics Lab 2019-04-03 | Killpack, Marc D., Ariel Kapusta, and Charles C. Kemp. "Model predictive control for fast reaching in clutter." Autonomous Robots 40, no. 3 (2016): 537-560.Killpack, Marc D., and Charles C. Kemp. "Fast reaching in clutter while regulating forces using model predictive control." In 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 146-153. IEEE, 2013.This video shows teleoperation of the robot Darci (7 degree of freedom arm with series elastic actuators) in an unmodeled canvas bag. We are using model predictive control with whole-arm tactile sensing. We also use a forward model of the dynamics and an explicit collision constraint to help control the forces. The video is in realtime.
Darci reaching quickly in artificial foliage with successes and failures Healthcare Robotics Lab 2019-04-03 | Killpack, Marc D., Ariel Kapusta, and Charles C. Kemp. "Model predictive control for fast reaching in clutter." Autonomous Robots 40, no. 3 (2016): 537-560.Killpack, Marc D., and Charles C. Kemp. "Fast reaching in clutter while regulating forces using model predictive control." In 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 146-153. IEEE, 2013.The robot Darci (with a 7 degree of freedom arm and series elastic actuators) reaching in artificial foliage using model predictive control with a tactile sensing sleeve. We use a full dynamic model of the robot arm in contact with the world. We also include a collision constraint to limit impact forces. Video is in real time. A histogram of forces measured with the tactile skin for successful and failed reaches is shown at the end of the video.
Higher Resolution Video of Cody Reaching in Force-Torque Clutter Field Healthcare Robotics Lab 2019-04-03 | Jain, Advait, Marc D. Killpack, Aaron Edsinger, and Charles C. Kemp. "Reaching in clutter with whole-arm tactile sensing." The International Journal of Robotics Research 32, no. 4 (2013): 458-482.
Combining Tactile Sensing and Vision to infer Dense Haptic Labels Healthcare Robotics Lab 2019-04-03 | The robot 'DARCI' uses a tactile sleeve and a Kinect to create a dense haptic map while reaching into a cluttered environment. As the robot comes in incidental contact with the objects in the environment, it acquires local haptic information using the sleeve and propagates the local information to update its estimate of the haptic properties of the visible surface using the Kinect.Bhattacharjee, Tapomayukh, Ashwin A. Shenoi, Daehyung Park, James M. Rehg, and Charles C. Kemp. "Combining tactile sensing and vision for rapid haptic mapping." In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1200-1207. IEEE, 2015.
Force and Thermal Sensing Skin Experimental Evaluation Healthcare Robotics Lab 2019-04-03 | Wade, Joshua, Tapomayukh Bhattacharjee, Ryan D. Williams, and Charles C. Kemp. "A force and thermal sensing skin for robots in human environments." Robotics and Autonomous Systems 96 (2017): 1-14.
Dusty: a mobile manipulator that retrieves dropped objects for people with motor impairments Healthcare Robotics Lab 2019-04-03 | tandfonline.com/doi/full/10.3109/17483107.2011.615374 CH King, TL Chen, Z Fan, JD Glass, CC Kemp. Dusty: an assistive mobile manipulator that retrieves dropped objects for people with motor impairments. Disability and Rehabilitation: Assistive Technology 7 (2), 168-179, 2011.People with physical disabilities have ranked object retrieval as a high-priority task for assistive robots. We developed Dusty, a teleoperated mobile manipulator that fetches objects from the floor and delivers them to users at a comfortable height. We tested the robot with 20 people with with amyotrophic lateral sclerosis (ALS) at the Emory ALS Center. Participants teleoperated Dusty to move around an obstacle, pick up an object and deliver the object to themselves. They successfully completed this task in 59 out of 60 trials (3 trials each) with a mean completion time of 61.4 seconds, and reported high overall satisfaction using Dusty (Mean = 6.8; 7-point Likert-type scale). Participants rated Dusty to be significantly easier to use than their own hands, asking family members, and using mechanical reachers. Fourteen of the 20 participants reported that they would prefer using Dusty over their current methods.
Data-Driven Haptic Perception for Robot-Assisted Dressing Healthcare Robotics Lab 2018-05-21 | Video from a controlled experiment on robot-assisted dressing in which forces at a robot's end effector were used to estimate and predict the outcome of a representative dressing sub-task. The sub-task was pulling a hospital gown onto a person's forearm.The work (http://pwp.gatech.edu/hrl/wp-content/uploads/sites/231/2016/06/haptic_perception_for_dressing_kapusta_et_al__ro-man__2016.pdf) was presented at the 2016 IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2016)
A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder Healthcare Robotics Lab 2017-10-30 | The video shows a PR2 robot detects an anomalous feeding execution during a robot-assisted feeding task. We first introduce a feeding system with multimodal sensors and a multimodal anomaly detector with a long short-term memory based variational autoencoder (LSTM-VAE). Prior to evaluation, we show how we recorded non-anomalous and 12 representative anomalous executions from able-bodied participants. The proposed detection system then successfully detects an anomaly in the context of robot-assisted feeding.Daehyung Park, Yuuna Hoshi, and Charles C. Kemp. “A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder”, 2018. [Under review]
Deep Haptic Model Predictive Control for Robot-Assisted Dressing Healthcare Robotics Lab 2017-10-10 | Z. Erickson, H. Clever, G. Turk, C. K. Liu, and C. C. Kemp, "Deep Haptic Model Predictive Control for Robot-Assisted Dressing", 2017.arxiv.org/abs/1709.09735
Tracking Human Pose During Robot-Assisted Dressing using Single-Axis Capacitive Proximity Sensing Healthcare Robotics Lab 2017-10-10 | Z. Erickson, M. Collier, A. Kapusta, and C. C. Kemp, "Tracking Human Pose During Robot-Assisted Dressing using Single-Axis Capacitive Proximity Sensing", 2017.arxiv.org/abs/1709.07957
A Multimodal Execution Monitor with Anomaly Classification for Robot-Assisted Feeding Healthcare Robotics Lab 2017-08-08 | This video shows the demonstration of a multimodal execution monitor for a robot-assisted feeding task. We also shows how the feeding system works with a person with severe quadriplegia and the process of anomaly data collection.Daehyung Park, Hokeun Kim, Yuuna Hoshi, Zackory Erickson, Ariel Kapusta, and Charles C. Kemp. “A Multimodal Execution Monitor with Anomaly Classification for Robot-Assisted Feeding”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2017)
What Does the Person Feel? Learning to Infer Applied Forces During Robot-Assisted Dressing Healthcare Robotics Lab 2017-03-14 | Accompanying video for the paper: "What Does the Person Feel? Learning to Infer Applied Forces During Robot-Assisted Dressing"Z. Erickson, A. Clegg, W. Yu, G. Turk, C. K. Liu, and C. C. Kemp, “What Does the Person Feel? Learning to Infer Applied Forces During Robot-Assisted Dressing”, 2017 IEEE International Conference on Robotics and Automation (ICRA), 2017.
Multimodal Execution Monitoring for Anomaly Detection During Robot Manipulation Healthcare Robotics Lab 2016-05-25 | D. Park, Z. Erickson, T. Bhattacharjee, and C. Kemp. “Multimodal Execution Monitoring for Anomaly Detection During Robot Manipulation”, IEEE International Conference on Robotics and Automation, 2016. (ICRA2016)
RSS Heat Transfer Video Healthcare Robotics Lab 2015-10-30 | This video is a collection of slides for RSS 2015 talk on Heat-transfer based material recognition from short duration contact with varying initial conditions.
The robot Darci autonomously extracting keys from unmodeled clutter Healthcare Robotics Lab 2015-04-02 | The robot Darci (with a 7 degree of freedom arm and series elastic actuators) extracting a set of keys from artificial foliage using model predictive control with a tactile sensing sleeve. We use a full dynamic model of the robot arm in contact with the world. We also include a collision constraint to limit impact forces. Video is in real time. The controller has no map of the environment and extracts the keys from a known target location using a magnet attached at the end effector.
Sparse Haptic Map Generation using Whole Arm Tactile Sensing - Real robot and map visualization Healthcare Robotics Lab 2015-04-02 | ...
Interleaving Planning and Control for Efficient Haptically-guided Reaching in Unknown Environments Healthcare Robotics Lab 2014-12-10 | The video shows a haptically-guided interleaving planning and control (HIPC) method with a haptic mapping framework using a simulated DARCI robot in Gazebo simulator. The contents of the video contain five different demonstrations; haptic sensing, haptic mapping, task-space planning & model predictive control, joint-space planning & model predictive control, a full version of reaching demonstration.Daehyung Park, Ariel Kapusta, Jeffrey Hawke, and Charles C. KempIEEE-RAS International Conference on Humanoid Robots (Humanoids 2014)
Learning to reach into the unknown: Selecting initial conditions when reaching in clutter Healthcare Robotics Lab 2014-12-10 | The video shows a reaching-in-clutter experiment with a PR2 robot in a foliage-aperture-clutter. The contents of the video contain tworeaching trials that Learning Initial Conditions (LIC) selects a passable aperture and a good initial configuration to reach a goal.Daehyung Park; Kapusta, A. ; You Keun Kim ; Rehg, J.M. ; Kemp, C.C.Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on.
Finding and Navigating to Household Objects with UHF RFID Tags by Optimizing RF Signal Strength Healthcare Robotics Lab 2014-09-22 | This video goes with the following paper: Travis Deyle, Matt Reynolds, and Charles C. Kemp, “Finding and Navigating to Household Objects with UHF RFID Tags by Optimizing RF Signal Strength.” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2014.ABSTRACT FROM THE PAPER: We address the challenge of finding and navigating to an object with an attached ultra-high frequency radio-frequency identification (UHF RFID) tag. With current off-the-shelf technology, one can affix inexpensive self-adhesive UHF RFID tags to hundreds of objects, thereby enabling a robot to sense the RF signal strength it receives from each uniquely identified object. The received signal strength indicator (RSSI) associated with a tagged object varies widely and depends on many factors, including the object’s pose, material properties and surroundings. This complexity creates challenges for methods that attempt to explicitly estimate the object’s pose. We present an alternative approach that formulates finding and navigating to a tagged object as an optimization problem where the robot must find a pose of a directional antenna that maximizes the RSSI associated with the target tag. We then present three autonomous robot behaviors that together perform this optimization by combining global and local search. The first behavior uses sparse sampling of RSSI across the entire environment to move the robot to a location near the tag; the second samples RSSI over orientation to point the robot toward the tag; and the third samples RSSI from two antennas pointing in different directions to enable the robot to approach the tag. We justify our formulation using the radar equation and associated literature. We also demonstrate that it has good performance in practice via tests with a PR2 robot from Willow Garage in a house with a variety of tagged household objects.FUNDING: This work was supported in part by National Science Foundation (NSF) awards CBET-0932592 and CBET-0931924, an NSF Graduate Research Fellowship Program award, and Willow Garage.
Henry Evans Shaving: Robots for Humanity Healthcare Robotics Lab 2013-10-30 | Henry Evans, a man with quadriplegia, shaves himself in his own home with a PR2 robot from Willow Garage using a system developed by members of the Healthcare Robotics Lab at Georgia Tech. This work is part of the Robots for Humanity Project, a collaboration between the Healthcare Robotics Lab, Willow Garage, Oregon State University, and Henry and Jane Evans.
Object Categorization using Forearm Tactile Skin Healthcare Robotics Lab 2013-09-04 | This video shows the initial result of Object categorization between soft-fixed, soft-movable, rigid-fixed, and rigid-movable categories. The robot can successfully classify single objects but fails to correctly classify multiple objects in simultaneous contact. We use PCA to reduce the dimensionality of the force data obtained from the forearm tactile skin and then use k-NN to classify the objects into four categories.
Rapid Categorization of Object Properties from Incidental Contact with a Tactile Sensing Robot Arm Healthcare Robotics Lab 2013-09-04 | This video shows the rapid categorization performance using HMMs while the robot reaches into clutter made of trunks and leaves. Details are given in the following paper:T. Bhattacharjee, A. Kapusta, J. M. Rehg, and C. C. Kemp, Rapid Categorization of Object Properties from Incidental Contact with a Tactile Sensing Robot Arm, IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2013(https://smartech.gatech.edu/handle/1853/49847)The robot uses data from the forearm tactile skin for online categorization. A taxel (tactile-pixel) is marked as a green dot if it is categorized as a leaf and as a brown dot if it is categorized as a trunk.
Reaching in Clutter with a High Degree of Freedom Robot Arm Healthcare Robotics Lab 2013-04-29 | This video shows the generality of our model predictive controller for reaching in clutter. Using the same parameters and formulation as reported in our IJRR paper for a three link simulated arm (see http://intl-ijr.sagepub.com/content/32/4/458) we were able to use the controller to effectively control six degrees of freedom as well.
Reaching with feedback from force-torque sensors or whole-arm tactile skin Healthcare Robotics Lab 2013-04-29 | ...
Simple Joint Space Impedance Control on Cody Healthcare Robotics Lab 2013-04-29 | This video shows the behavior of our robot Cody when it is maintaining a fixed virtual trajectory using simple joint space impedance control.
Online Stiffness Estimation Healthcare Robotics Lab 2013-04-29 | The robot Cody estimates the stiffness of the contact online with the hardware-in-the-loop skin simulation testbed while reaching to a goal location.Details of the system shown in this video are in Sec. VI-C1 of this paper:Manipulation in Clutter with Whole-Arm Tactile Sensing, Advait Jain, Marc D. Killpack, Aaron Edsinger, and Charles C. Kemp. Under Reviewhttp://www.hsi.gatech.edu/hrl/pdf/haptic_manipulation_clutter.pdfThis is joint work by the Healthcare Robotics Lab, Georgia Tech and Meka Robotics.
