Much in the same way, robots are now able to intelligently maneuver within clutter, gently making contact with objects while accomplishing a task. This new control method has wide applications, ranging from robots for search-and-rescue operations to assistive robotics for people with disabilities.
“Up until now, the dominant strategies for robot manipulation have discouraged contact between the robot’s arm and the world,” said Charlie Kemp, lead researcher and associate professor in the Coulter Department of Biomedical Engineering at Georgia Tech and Emory University. “Instead of avoiding contact, our approach enables the arm to make contact with objects, people and the rest of the robot while keeping forces low.”
Kemp, director of Georgia Tech’s Healthcare Robotics Lab, along with his graduate students and researchers at Meka Robotics, has developed a control method that works in tandem with compliant robotic joints and whole-arm tactile sensing. This technology keeps the robot’s arm flexible and gives the robot a sense of touch across its entire arm.
With their control method, Kemp’s robots have performed numerous tasks, such as reaching through dense artificial foliage and a cinder block representative of environments that search-and-rescue robots can encounter.
A publication describing the research, “Reaching in Clutter with Whole-arm Tactile Sensing,” appears in this month’s edition of the International Journal of Robotics Research.
Kemp's lab also has promising results that could impact the future of assistive robotics. They have developed tactile sensors made out of stretchable fabric that covers the entire arm of a robot. In a preliminary trial with the new control method and sensors, Henry Evans, a person with quadriplegia, used the robot to perform tasks for himself. He was able to pull a blanket over himself and grab a cloth to wipe his face, all while he was in bed at his home.
This trial was conducted as part of the Robots for Humanity project with Willow Garage. In order to ensure safety, researchers from Kemp’s lab closely monitored the activities. This research has been accepted and will be presented at the International Conference on Rehabilitation Robotics in June.
“I think it’s a good safety feature because it hardly presses against me even when I tell it to,” Evans said after the trial. “It really feels safe to be close to the robot.”
Evans was also impressed by how the robot’s arm “just wriggles around obstacles.”
Kemp’s research team has also released the designs and code for the sensors and controller as open source hardware and software so that researchers and hobbyists can build on the work.
The research is part of an ongoing effort to create a new foundation for robotics, where contact between the robot’s arm and the world is encouraged.
“Our belief is that this approach is the way of the future for robots,” said Kemp, who is also a member of Georgia Tech’s Center for Robotics and Intelligent Machines. “It is going to allow robots to better operate in our homes, our workplaces and other complex environments.”
This research is funded by the DARPA Maximum Mobility and Manipulation (M3) Contract W911NF-11-1- 603. The assistive technology research is also funded in part by NSF CAREER award IIS-1150157, NSF grant CNS-0958545, an NSF GRFP and Willow Garage.
CITATIONS: Advait Jain, Marc D Killpack, Aaron Edsinger, and Charles C Kemp. Reaching in Clutter with Whole-arm Tactile Sensing. The International Journal of Robotics Research, April 2013, 32: 458-482, doi:10.1177/0278364912471865
Phillip M. Grice, Marc D. Killpack, Advait Jain, Sarvagya Vaish, Jeffrey Hawke, and Charles C. Kemp. Whole-arm Tactile Sensing for Beneficial and Acceptable Contact During Robotic Assistance. Accepted to the 13th International Conference on Rehabilitation Robotics (ICORR), June 2013.
]]>
]]>
“Technology allows us to check our weight, blood-sugar levels and blood pressure, but not our own cognitive abilities,” said project leader Ellen Yi-Luen Do. “Our ClockMe System helps older adults identify early signs of impairment, while allowing clinicians to quickly analyze the test results and gain valuable insight into the patient’s thought processes.”
Georgia Tech’s ClockMe system eliminates the paper trail and computerizes the test into two main components: the ClockReader Application and the ClockAnalyzer Application. Click here to see a video demo.
ClockReader is the actual test and is taken with a stylus and computer or tablet. The participant is given a specific time and instructed to draw a clock with numbers and the correct minute and hour hands. Once completed, the sketch is emailed to a clinician, who uses the ClockAnalyzer Application to score the test. The software checks for 13 traits. They include correct placement of numbers and hands without extra markings. People with cognitive impairment frequently draw clocks with missing or extra numbers. Digits are sometimes drawn outside of the clock. The time is often incorrect.
In addition to scoring automatically and consistently, ClockAnalyzer records the duration of the test and the time between each stroke. The software also replays the drawing in real-time, allowing a clinician to watch the drawing being created to observe any behavior abnormality.
“The traditional paper-and-pencil test is usually overseen by a technician and later scored by a clinician, who scores the test based only on the finished drawing,” said Do, a professor in Georgia Tech’s Colleges of Computing and Architecture. “By looking at the sketch, the scorer is not able to decipher whether the person struggled to remember certain numbers while drawing the clock. The ClockMe system’s timing software highlights those delays.”
And, because they’re saved electronically, the drawings can be used to easily compare a person’s cognitive ability progress or regression over time. Do’s research found that traditional tests are often filed in a folder and are rarely used for future comparison.
The ClockMe system was initially tested at the Emory Alzheimer’s Disease Research Center in Atlanta, where it’s currently being used in addition to the traditional paper-and-pencil test. Despite a lack of computer literacy, all of the elderly patients who used the software during the study said they had no problems with the pen-based, computer technology.
“For this reason, as well as the ability to send the drawings directly to clinicians for convenient scoring, we envision ClockMe as a viable tool for home-based screening,” said Do. “America’s health care costs are expected to soar as baby boomers become senior citizens. If a screening tool can be used at home, unnecessary trips to clinics can be eliminated and medical expenses can be saved.”
Do and her colleagues are hoping to commercialize the project in the future. Their research was published in September’s Journal of Ambient Intelligence and Smart Environments.
This project is supported by the National Science Foundation (NSF) (Award Number SHB-1117665). The content is solely the responsibility of the principal investigators and does not necessarily represent the official views of the NSF.
]]>
One of the tools—a system that uses special gaze-tracking glasses and facial-analysis software to identify when a child makes eye contact with the glasses-wearer—was created by combining two existing technologies to develop a novel capability of automatic detection of eye contact. The other is a wearable system that uses accelerometers to monitor and categorize problem behaviors in children with behavioral disorders.
Both technologies already are being deployed in the Center for Behavior Imaging’s (CBI) ongoing work to apply computational methods to screening, measurement and understanding of autism and other behavioral disorders.
Children at risk for autism often display distinct behavioral markers from a very young age. One such marker is a reluctance to make frequent or prolonged eye contact with other people. Discovering an automated way to detect this and other telltale behavioral markers would be a significant step toward scaling autism screening up to much larger populations than are currently reached. This is one goal of the five-year, $10 million “Expeditions” project, funded in fall 2010 by the National Science Foundation under principal investigator and CBI Director Jim Rehg, also a professor in Georgia Tech’s School of Interactive Computing.
The eye-contact tracking system begins with a commercially available pair of glasses that can record the focal point of their wearer’s gaze. Researchers took video of a child captured by a front-facing camera on the glasses, worn by an adult who was interacting with the child. The video was then processed using facial recognition software available from a second manufacturer. Combine the glasses’ hard-wired ability to detect wearer gaze with the facial-recognition software’s ability to detect the child’s gaze direction, and the result is a system able to detect eye contact in a test interaction with a 22-month-old with 80 percent accuracy. The study was conducted in Georgia Tech’s Child Study Lab (CSL), a child-friendly experimental facility richly equipped with cameras, microphones and other sensors.
“Eye gaze has been a tricky thing to measure in laboratory settings, and typically it’s very labor-intensive, involving hours and hours of looking at frames of video to pinpoint moments of eye contact,” Rehg said. “The exciting thing about our method is that it can produce these measures automatically and could be used in the future to measure eye contact outside the laboratory setting. We call these results preliminary because they were obtained from a single subject, but all humans’ eyes work pretty much the same way, so we’re confident the successful results will be replicated with future subjects.”
The other new system, developed in collaboration with the Marcus Autism Center in Atlanta and Dr. Thomas Ploetz of Newcastle University in the United Kingdom, is a package of sensors, worn via straps on the wrists and ankles, that uses accelerometers to detect movement by the wearer. Algorithms developed by the team analyze the sensor data to automatically detect episodes of problem behavior and classify them as aggressive, self-injurious or disruptive (e.g., throwing objects).
Researchers first developed the algorithms by putting the sensors on four Marcus clinic staff members who together performed some 1,200 different behavior instances, and the system detected “problem” behaviors with 95 percent accuracy and classified all behaviors with 80 percent accuracy. They then used the sensors with a child diagnosed along the autism spectrum, and the system detected the child’s problem-behavior episodes with 81 percent accuracy and classified them with 70 percent accuracy.
“These results are very promising in leading the way toward more accurate and reliable measurement of problem behavior, which is important in determining whether treatments targeting these behaviors are working,” said CSL Director Agata Rozga, a research scientist in the School of Interactive Computing and co-investigator on the Expeditions award. “Our ultimate goal with this wearable sensing system is to be able to gather data on the child’s behavior beyond the clinic, in settings where the child spends most of their time, such as their home or school. In this way, parents, teachers and others who care for the child can be potentially alerted to times and situations when problem behaviors occur so that they can address them immediately.”
“What these tools show is that computational methods and technologies have great promise and potential impact on the lives of many children and their parents and caregivers,” said Gregory Abowd, Regents’ Professor in the School of Interactive Computing and a prominent researcher in technology and autism. “These technologies we are developing, and others developed and explored elsewhere, aim to bring more effective early-childhood screening to millions of children nationwide, as well as enhance care for those children already diagnosed on the autism spectrum.”
Both technologies were presented in early September at the 14th ACM International Conference on Ubiquitous Computing (Ubicomp 2012). Among the other devices under study at CSL are a camera/software system that can track children’s facial expressions and customized speech analysis software to detect vocalization patterns.
For more information on behavioral imaging, visit the Georgia Tech/NSF website on computational behavioral science at http://www.cbs.gatech.edu. For information or to volunteer for one of CBI’s ongoing studies, visit the Child Study Lab website at http://childstudy.hsi.gatech.edu.
]]>]]>
The University System of Georgia Board of Regents grants the professorships to outstanding, tenured full professors based on excellence in research and contributions to their professions and institutions.
"We are very proud of our new Georgia Tech Regents' Professors," said Rafael L. Bras, provost and executive vice president for Academic Affairs. "By definition, they represent the very best among our extraordinary faculty — they are educators, academicians and scholars of the first order."
Abowd, a distinguished professor in the School of Interactive Computing, arrived at Tech in 1994 and quickly developed a research agenda on the applications of novel technologies in living laboratories such as the classroom and home. Since 2002, much of his research has been devoted to challenges linking information technologies to autism. Abowd established the Atlanta Autism Consortium in August 2008, which helped to unite Atlanta’s many autism-related constituencies.
He was selected as a Rhodes Scholar in 1986 and, after completing his research studies at the University of Oxford, worked from 1989 to 1992 as a research associate with the Human-Computer Interaction Group in the Department of Computer Science at the University of York in England. From 1992 to 1994, Abowd was a postdoctoral research associate with the Software Engineering Institute and the Computer Science Department at Carnegie Mellon University.
"I am very grateful for the recognition of this Regents' Professorship, because it recognizes the importance of the work my colleagues, students and I have been doing," Abowd said. "I am also very grateful because this recognition was initiated by my peers, and it is an indication of their respect for what I have accomplished over the years at Georgia Tech."
Thursby, a research associate of National Bureau of Economics Research since 1987, is currently Hal and John Smith Chair of Entrepreneurship in the Scheller College of Business. Her research on innovation and technology transfer has been used in congressional, National Institute of Health and U.S. National Academies policy discussions.
One of her major contributions to Tech since arriving in 2002, has been founding the internationally acclaimed Technological Innovation: Generating Economic Returns (TI:GER) program. TI:GER is a collaboration between the Institute and Emory University and has received multiple awards including the Academy of Management Entrepreneurship Pedagogy Award in 2006. The program teams PhD students in science and engineering with MBA and JD students in an experiential curriculum focused on the intersection of technical, legal and business issues and innovation.
Prior to arriving at Tech, Thursby was the Burton D. Morgan Chair of International
Policy and Management at Purdue University and has held faculty appointments at the
University of Michigan, Ohio State University, Syracuse University and North Carolina State University.
"I feel quite honored and grateful," Thursby said. "At Georgia Tech, I get to work with great colleagues and students in an environment that can't help but make one productive."
]]>"The EFRI research teams will probe some profound aspects of the interface of biology and engineering," said Sohi Rastegar, director of EFRI. "If they are successful, the principles and theories uncovered in their investigations could unlock many technological opportunities."
This year, 14 transformative, fundamental research projects were awarded EFRI grants in two emerging areas: technologies that build on understanding of biological signaling, and machines that can interact and cooperate with humans.
The three Georgia Tech projects include:
The therapeutic robot could enhance, assist and improve motor skills in humans with varying motor capabilities and deficits. The goal of the project is to program a humanoid rehabilitation robot to perform a "partnered box step," which is a defined pattern of weight shifts and directional changes, solely based on interpreting movement cues from subtle changes in forces between the hands and arms of the robot and the person.
To do this, researchers at Georgia Tech and Emory University will study how humans use their muscles to walk, balance and generate force signals with the hands for guidance when moving in cooperation with another person. They will also study "rehabilitative partnered dance," which has been specifically adapted to help improve gait and balance in individuals with motor impairments.
"Our vision is to develop robots that will interact with humans as both assistants and movement therapists," explained principal investigator Lena Ting, an associate professor in the Wallace H. Coulter Department of Biomedical Engineering at Georgia Tech and Emory University. "We expect our project to have a long-term impact on quality of life of individuals with movement difficulties, such as those caused by Parkinson's disease, stroke and injury by improving fitness, motor skills and social engagement."
Working with Ting on the project are Emory University School of Medicine (geriatrics) assistant professor Madeleine Hackney, Coulter Department of Biomedical Engineering assistant professor Charlie Kemp and Georgia Tech School of Interactive Computing assistant professor Karen Liu.
For the second project, researchers at Georgia Tech and The City College of New York will investigate devices for "alternative perception" and the principles underlying the human-machine interaction. Alternative perception combines electronics and the other senses to emulate vision. In addition to aiding the visually impaired, the findings are expected to have other applications, such as the development of intelligent robots.
The researchers plan to untangle how humans learn to coordinate input from their senses -- e.g. vision, touch -- with movements, like reaching for a glass or moving through a crowded room. They will then map out how machines, such as robots and computers, learn similar tasks, to model devices that can assist humans.
The team envisions a multifunctional array of sensors on the body and has already developed prototypes for some of the devices. The full complement of wearable sensors would help a sightless person navigate by conveying information about his or her surroundings.
The researchers hope their findings on perception, and the prototypes they develop, will spawn a raft of wearable electronic devices to help blind people "see" their environment at a distance through touch, hearing and other senses. The technology would also benefit sighted individuals who must navigate in poor visibility, such as firefighters and pilots.
Principal investigator Zhigang Zhu, professor of computer science and computer engineering in City College's Grove School of Engineering, will collaborate with City College professor of psychology and director of the Program in Cognitive Neuroscience Tony Ro, City College professor of electrical engineering Ying Li Tian, Georgia Tech Woodruff School of Mechanical Engineering professor Kok-Meng Lee, and Georgia Tech School of Applied Physiology associate professor Boris Prilutsky.
The third project will address a fundamental question of developmental biology: what controls the spatial and temporal patterns of cell differentiation? Answering this question will lead to a better understanding of the basic principles of embryogenesis, explain origins of developmental disorders, and provide guidelines for tissue engineering and regenerative medicine.
The research will be conducted by principal investigator and Princeton University Department of Chemical and Biological Engineering associate professor Stanislav Shvartsman, Georgia Tech School of Chemical and Biomolecular Engineering associate professor Hang Lu, New York University Department of Biology professor Christine Rushlow, and University of Illinois at Urbana Champaign Department of Computer Science associate professor Saurabh Sinha.
Scientists know that among an embryo's first major developments is the establishment of its dorsoventral axis, which runs from its back to its belly. The researchers plan to study how this axis development unfolds -- specifically the presence and location of proteins during the process, which give rise to muscle, nerve and skin tissues.
To enable large-scale quantitative analyses of protein positional information along the dorsoventral axis, Lu and Shvartsman will further develop a microfluidic device they previously designed to reliably and robustly orient several hundred embryos in just a few minutes.
"By understanding this system at a deeper, quantitative level, we will elucidate general principles underlying the operation of genetic and multicellular networks that drive development," said Lu.
Research News & Publications Office
Georgia Institute of Technology
75 Fifth Street, N.W., Suite 314
Atlanta, Georgia 30308 USA
Media Relations Contacts: Abby Robinson (abby@innovate.gatech.edu; 404-385-3364) or John Toon (jtoon@gatech.edu; 404-894-6986)
]]>