Final Robotics Project: Robots in Assistive Technology
Design objective: Design and build a robot that can assist a person with a disability or an elderly person in accomplishing a daily task.
Definition: "Assistive technology (AT), the field of innovations that removes barriers or bypasses impediments for people with disabilities, can range from a simple stick or magnifying glass, to sophisticated apperati capable of sensing surroundings and performing complicated tasks. Such technology can be applied to assist people in accomplish daily tasks around the home or in a vocational setting." (Solomon, see http://www.aaai.org/AITopics/html/assist.html for more information)
Requirements:
The robots will be exhibited the during the final exam pewriod scheduled for this class (Thursday Mar. 20, 2008. 12:30 -14:20). It should be documented as the other projects have been in the blog. The key difference between this and the previous projects is that you are defining your own set of objectives and requirements. You will therefore need to spend more time documenting both your design objectives and how you accomplished those objectives with the robots. It might be helpful to put it in the form of user needs or criteria, however that is not required.
The attached articles may help you get some ideas. The originals on the web have pictures. You can also do your own searches. I just used google with "robots assistive technology" as the keywords and easily found good ideas.
The following is from: Robotics Trends: Robot technology that assists, entertains and protects us. For more details than the text below, follow this link.
Sunday, September 07, 2003 - 11:25 AM
Robotics technology has broken out of the factory floor and is being employed in novel ways to assist the disabled. While few products are standalone robots per se, they all employ advanced robotic technology.
By Karen Solomon
Assistive technology (AT), the field of innovations that removes barriers or bypasses impediments for people with disabilities, can range from a simple stick or magnifying glass, to sophisticated apperati capable of sensing surroundings and performing complicated tasks. Such technology can be applied to assist people in accomplish daily tasks around the home or in a vocational setting.
Robotic technology is moving quickly from the factory floor, where for years robots have sprayed paint, welded or assembled manufactured goods in a highly structured environment, to the unstructured environments in the home and workplace, where robotic technology is being applied in novel new ways. Assistive technology is no exception. The AT community is buzzing with innovation that serves the disabled by allowing them to accomplish goals independently. "People are comfortable enough with robotics that they’re going beyond the highly industrial culture," says Chris Morse, co-founder of Yobotics, developers of the leg-assisting Robowalker. "Robotics technology is poised for rapid growth and maturing to be cross-functional. We're finally seeing it move into the public sector and being embraced by other fields."
Robotics has come a long way from the assembly line into the day-to-day life of personal assistance. For persons who lack the required physical, sensory, or mental capabilities demanded by most cultural platforms, the availability and emergence of assistive robotics technology opens whole new vistas and increases their quality of life. What follows is a overview of a few of the many robotic innovations that are emerging that assist those with a wide range of disabilities.
A Helping Hand
Many people who are wheelchair bound also often have incomplete use of their hands either through a loss of strength, fine motor control or dexterity, of some combination of such. This fact is not lost on manufacturers. While assistive robotics is a relatively new field, a number of commercially available robotic devices that make the lives of the wheelchair bound more independent have been produced. One such robotic device is Rehabilitation Technologies’ Raptor.
With the Raptor, individuals can maneuver a robotic arm attached to their wheelchairs and reach for, grasp and manipulate objects in their environment. When not in use, the arm folds up neatly, reducing its profile. The arm has excellent range of rotation, flexion and extension, and is able to reach objects high above the head, as well material on the floor. Control of the robotic arm is accomplished through a joystick or keypad, or via a sip-and-puff interface.
The Handy Glove Translator
Ryan Patterson, a high school senior in 2001 with a flair for competitive science fairs, observed a group of deaf people ordering a meal in a fast food restaurant with the assistance of human interpreter. He recalls, "It was obvious to me that they could be much more independent if they had an electronic interpreter." Thus, Patterson set out on a six-month endeavor to invent a glove that transmits the sign language alphabet into text on a display screen.
The result of Patterson’s work was a leather golf glove equipped with about ten flex sensors which "read" each signed letter based on how the user bends the sensors (like voice recognition software, the glove must be trained for each individual user’s "voice"). The captured data is then wirelessly transmitted via radio frequency to a receiver/display, approximately the size of a candy bar with a black and white read-out, of Patterson’s own design. Thus, letter by letter, a finger-spelling person can have their message translated into written text.
Patterson’s Glove Translator was a huge hit at science fairs - he was the recipient of the first place $103,000 scholarship in the Siemens Westinghouse Science and Technology competition, and first place winner of the $100,000 Intel Science Talent Search scholarship. He also received heaps of media coverage and other awards.
While Patterson’s device is effective at translating the alphabet, it is unable to read and translate American Sign Language, the most common language of the deaf and hard-of-hearing. "Eventually it will do more. I’m still working on it," says Patterson. He also notes that ASL is a complicated language, involving not only finger movements, but arm motions and gestures that often use the upper body, along with facial expressions. Like electronic language translators for travelers, it could be tough to get the translation exactly right. Says Patterson, "Just like any other language, ASL is complicated."
Patterson is not deaf, and did not become a student of sign language until recently. He is, however, working on becoming a fluent communicator. Patterson notes, “I just wanted to develop something that I thought could help people.”
Ryan Patterson applied for a patent for the Glove Translator over a year ago, and is still waiting for that to come through, a process that will take a couple of years. Commercial investor interest in the device has been off and on, but he would like to take the device to market eventually. While he waits for patent approval, Patterson is focusing on other inventions and concentrating on his studies. He will be going into his second year at the University of Colorado at Boulder as a student of electrical and computer engineering.
In Step With the Robowalker
Chris Morse has always been a leg man. In 2000, he and three other graduates of MIT’s Leg Laboratory, part of the Artificial Intelligence Lab, formed their own company, Yobotics, to focus on robotic legs and orthotics, robotic legs that help people with weak legs or leg injuries to ambulate independently.
Yobotics is in the process of developing the Robowalker, a power-assisted wearable device to help give legs strength, support, and endurance for the elderly and those feeling the effects of muscular weakening diseases, such as Multiple Sclerosis and Muscular Dystrophy.
With Robowalker, the leg and foot are webbed in a series of artificial, exoskeleton springy tendons and muscles "the company’s proprietary Low Impedance Force Control technology. Power to react is inherent in the device and used only when needed through sensors in the foot. The device knows when the user is going up stairs, for example, and gives bursts of muscular energy through the brace when needed. Users look like the quintessential cyborg" ensconced in pistons, sensors, and muscles working on their own.
Morse is quick to point out that the Robowalker, or its scaled-down cousins, the Roboknee or Roboankle, aren’t appropriate for paraplegics, as the user must have the ability to put their leg where it needs to go. But he also points out that if the company’s project “ever comes to fruition in its grandest sense,” at some point they would love to develop a device that can actually do the walking.
For now, the Robowalker prototype has had some impressive trials, but also some setbacks. For one, the batteries to power the device do not allow for a lengthy period of use – roughly 30-40 minutes of wireless assisted walking before requiring a new set of batteries or a recharge. In addition, says Morse, the cost of the device makes it prohibitively expensive for most people. Although Robowalker is still in development, and thereby it is premature to determine exactly what its final price point will be, Morse describes the $10,000 range a “reasonable estimate”.
After three years of funding for the project from the non-profit organization Power Prosthetics, Yobotics is looking for a new resource to further the company’s research. Without continued revenue to make it work, says Morse, the project might not have a leg to stand on. Still, Morse is optimistic that with the right resources and support, he and his team can continue their work in orthotics and give the Robowalker legs. Morse acknowledges the competition in the field of robotic orthotics and expects rapid growth for the nascent market. “It is coming”, predicts Morse. “The number of people working on it is increasing every day.”
… Reading, Talking, Learning
"There is such a stigma about not being smart, about being a dummy", says Jennifer Edge, a K-12 teacher at the South Shore Education Collaborative in Massachusetts. She continues, the sarcasm just dripping from her voice, "and 14 and 15 year-old boys just love to have someone baby them. Of course kids of that age want as much independence as they can get away with. But if they’re kids with a learning disability, dyslexia, or if they just have difficulty reading and processing written materials, historically they have needed more teacher babying than the average teen. Someone needs to read to them, pause to help the student look up words, in short, be the always-on teacher, standing over their shoulder telling them how to do it".
With the Kurzweil 3000, Edge saw an opportunity to offer some of her students the independence and study aid that they craved. The Kurzweil 3000, by Kurzweil Educational Systems in Bedford, MA, is software that works with a scanner and desktop computer to help students with language-based learning disabilities focus on their reading and get more out of the text.
Work with the Kurzweil system begins with a teacher or student scaning a book or other written materials. Students can then can have a computer read text to them and simultaneously see the words on the screen. A built-in dictionary and synonyms list keeps students focused on the material. In addition, when a student writes, they can have their words read to them aloud to insure that their text is comprehensive, and take advantage of the built-in spell-checker and other word- processing tools. Notes Edge, “Many of my students require an auditory cue while they're reading, taking tests, or doing their work. They may come across a word they don't know while reading, but hearing it helps them to understand. With this level of assistance, they can perform a lot better in their academic world.”
In addition to serving kids with special learning needs, the Kurzweil 3000 system can also work with physically-impaired students, providing text magnification for the visually-impaired, or alternatively, computerized page-turning methods for those who cannot physically turn a page or shuffle papers.
The Kurzweil 3000 has been available to the public since 1996. For Windows machines, version 7 was just released this past January, and for the Macintosh, version 2 is expected to launch this fall. Subsequent improvements, says Mike Gorman, program manager for Kurzweil 3000 for the Macintosh and senior software engineer for the Windows version, will focus more on centralized networking capabilities, allowing a teacher or administrator to sit in one place and administer the entire class, rather than bouncing from machine to machine. He also anticipates that future versions will overhaul some of the writing tools.
Edge admits that the Kurzweil system is not for every student "some prefer to have the hard copy in their hands or they dislike interacting with a computer. But for those who do rely on the system for reading, listening, writing, and studying, she has seen marked improvement in her student’s performance. “What a difference from the beginning of the year to the end!’", Edge notes with satisfaction.
Reaching for the Stairs
Dean Kaman, one of our nation’s foremost inventors, is probably best known for developing the Segway Human Transporter, the gravity defying, upright scooter with oversized wheels that was shrouded in secrecy while under development. But the same technology that propels the Segway – the microprocessor assisted gyroscopic wheels that allows the Segway to balance the same way the human body does - was incorporated into one of Kaman’s earlier, and possibly more high- impact, inventions.
In 1995 Kaman’s company, DEKA Research and Development, partnered with Johnson & Johnson to develop the Independence iBot Mobility System, a product of Independence Technologies. The iBot, a type of wheelchair on steroids, is a revolution in transportation for those that use wheelchairs offers, providing unprecedented independence and mobility. Not only does the iBot operate as a slimmed-down standard wheel chair, but it also has 4-wheel drive mechanism, designed for rough terrain like sand and gravel, uneven surfaces, as well as slopes and hills. But most incredibly, the iBot has two gyroscopic wheels that balance the chair with the stability and reliability of a standing person. When working together, these wheels can scale staircases of any length, either with the use of a hand rail or with an assistant. (A small amount of physical strength in the upper body is required.)
When not using both wheels to scale stairs, the two wheels stack one on top of the other and allow the iBot to elevate the user to a normal standing height, enabling them to see in a crowd and reach items from a top shelf. To see this is incredible – it’s as if two small unicycle wheels were stacked vertically to balance a 200-pound wheelchair with a 200pound person.
The iBot is like nothing else the disabled community has ever seen, and the excitement and anticipation surrounding its release has been tremendous in the US, UK, Norway, and Sweden. Clinical studies of real users began in 1999 and lasted for four years, ending with successful results. Because it is a medical device and not just transportation for able-bodied people (like the Segway), the iBot must have FDA approval. The company is anxiously awaiting approval, which is expected this Fall.
Dean Kamen once told John Hockenberry of MSNBC News, "I don’t work on a project unless I believe that it will dramatically improve life for a bunch of people." This philanthropic pursuit of discovery seems to be working well for Kaman; he holds more than 150 patents in the US and abroad, covering everything from medical devices and climate control systems, to helicopter design. In addition to his full-time work with DEKA R&D, Kaman is also the founder of FIRST, For Inspiration and Recognition of Science and Technology, an organization devoted to inspiring young people to enter the field of robotics and technology with educational programs and competitive robotic events.
Karen Solomon is a San Francisco based technology writer who focuses on assistive technology. She can be reached at ks@ksolomon.com.
© 2005 Robotics Trends, 10 Riverbend Road, Upton, MA 01568 - P: (508) 529-4197 - F: (508) 464-0234 Email Us | Login
Wednesday, April 07, 2004 - 08:14 PM Copyright 2004 P.G. Publishing Co.
By Gary Rotstein
The group in their 80s and 90s studied the pictures of elder-care robot Pearl, glanced at the robotocized walker awaiting a test in the corner and listened to a fledgling robotocist with the youthful features of Elroy Jetson describe the future.
And then the residents of the Longwood at Oakmont retirement community peppered blue-jeaned, sneakered Elroy, actually Jared Glover, a Carnegie Mellon University senior and research programmer in its Center for Automated Learning and Discovery, with questions. The walker is equipped with sonar detectors, a laser range finder and mapping software to figure out where it's going, even if the person gripping it doesn't know.
Would it sense a stair to avoid a tragic fall?
Nope.
Can it bring a chair to relieve walking fatigue?
Uh, no.
What century is it going to be before futuristic versions of household help are actually in someone's home?
This one.
If the future isn't now, it is getting closer all the time. With an explosion of the senior population due in two decades, researchers are looking for ways to match the technology that science-fiction writers anticipated years ago with the practical benefits a frail, elderly person living alone might need to continue living at home.
So instead of focusing on robots that work on lunar surfaces or ocean floors, a research team from Carnegie Mellon, the University of Pittsburgh, University of Michigan and Stanford University has spent the past four years tinkering with devices that trek across carpets and kitchen floors.
At the March 16 national conference of the Center for Aging Services Technologies in Washington, D.C., the team displayed the high-tech walker dubbed IMP; a related, handheld memory device that prompts people on things they should be doing; and Pearl herself, the object of greatest attention. With movable facial features mounted atop her 4-foot high collection of computers, motors, plugs and wires, she's the product that most closely resembles the image conjured by the term "robot."
Pearl has visited the upscale Longwood residence several times since the research team received a $1.4 million National Science Foundation grant for the Personal Robotic Assistants for the Elderly project. The researchers wanted to assess, first of all, how people who grew up before mainframes would take to interacting with devices that looked like props or mechanized cast from "Star Wars."
If these well-heeled and well-educated people are any fair indication of the overall senior population -- and researchers aren't certain they are -- then the likes of Pearl should have no trouble fitting in.
"I'm fascinated. I just think it has endless possibilities," Betty Niedringhaus, 85, a former Carnegie Museum employee, said of the new technology. She was among those who took a turn letting the walker guide her toward Longwood's gift shop as it displayed a shifting arrow on a screen to point the way.
Pearl herself has had fits and starts, as a second-generation prototype suffering from the natural turnover in the project of some its key computer scientists, as well as a serious hard-drive crash last year. She's $100,000 worth of circuitry and hardware that doesn't yet hear, talk, recall and react the way her inventors envision, and won't do so for a decade or possibly much longer.
Like football scouts appraising a raw, strong-armed quarterback, Pearl's own researchers disagree on her timetable and practical potential.
At her most fundamental, she's already able to guide herself through an area at a pace of up to 50 centimeters a second -- a slow walk, for humans -- while avoiding objects in her path. When her hardware and software are working well, Pearl can verbalize scripted reminders to people, such as it's time to take their medicine.
Down the road, programmers aim to give her the intelligence to monitor people and react to unusual variations in behavior. If a person hasn't visited the bathroom in a long time, a reminder will be offered. If a person hasn't come out of the bathroom or moved from a chair in an unusually long amount of time, Pearl would seek an explanation and summon help if there's no answer. In the long range, she might have manipulating arms, instead of her current siderails, to pick up or move things for people.
None of these is easy, said professor Sebastian Thrun, pioneer of the project at Carnegie Mellon, who has remained involved since relocating to Stanford to run its artificial intelligence lab.
The kind of human interaction contemplated for Pearl is light years beyond the original industrial purposes of robots -- repeating the same welding or stamping or sorting motion without allowing any deviation. It's even far beyond the type of work done by the Mars Rover or some robot cleaning nuclear waste, with humans guiding their activities from a distance.
"From a robotic domain, topics such as living with a person, sharing the same space, interacting with a person, are the cutting edge in robotics," Thrun said. "When it's dealing with a person, all of these uncertainties come up. What does the person want? Where does the person go next, and how does it find the person? ... It's like a dog that has to learn to adapt to you and understand your desires."
Not all of those involved in the project are computer experts. Judy Matthews, a Pitt assistant professor of nursing, uses a community health background to provide input on what elderly people want and need. She has seen some of the Longwood residents' impatience on Pearl's visits, when the robot's movements or reactions are out of sync with people's expectations.
She and others leading the project have become convinced that the new-wave walker, one that knows how to move itself out of the way when unneeded and return to its user when summoned, will be the first practical result of Pearl-related work. Offering guidance as well as support to users, once it has mapped out the rooms, halls and other features of its location, the IMP can free up attendants in a long-term care facility for more important things than walking someone to a dining room.
Matthews stressed that such an invention was meant to supplement what professional or family caregivers do, not replace them. The original term for the project, Nursebot, attracted chagrin from some members of the nursing profession who didn't see the robots as their equivalent, and Matthews has shied away from using that term.
"We describe them now as intelligent assistive devices for the elderly," she said.
The IMP will become more useful, researchers say, once advances are made to coordinate its use with a handheld piece of artificial intelligence under development by University of Michigan professor Martha Pollack, formerly an award-winning faculty member at Pitt. Sensor technology will try to detect how long it's been since people did essential tasks and offer reminders, the same as Pearl may someday do but without all her other complex bells, whistles, wheels and motors.
Carnegie Mellon's Sara Kiesler, a psychologist and professor of computer science involved in the project, said a lot of smaller, simpler achievements in helping older adults may be the real fruit of the research, instead of counting on Pearl as the kind of multitasking, interactive domestic servant that Luke Skywalker enjoyed.
Already, vacuum cleaners have come out that can clean a rug similarly to Jane Jetson's robot, without anyone guiding them. No one cares that they don't look like robots, although Kiesler is heading up research exploring just how Pearl's appearance and demeanor affects people.
"I don't need for it to have a human face and to pat it," said Niedringhaus, the Longwood resident. "I wouldn't want anyone to fall in love with something like that."
Copyright 2004 P.G. Publishing Co.
Copyright © 2002 LexisNexis, a division of Reed Elsevier Inc.