Paving Way for Future Rehab Tool, Children Teach Robot to Play Game on Tablet
A Georgia Institute of Technology (Georgia Tech) project allows children to program a small humanoid robot to play a game using a tablet; it may one day also serve as a rehabilitation tool and assist children with disabilities. Using an Android tablet, the children teach the robot how to play the application Angry Birds, dragging their fingers across the screen.
See the technology in action in this video
The robot, according a news release from Georgia Tech, watches children play the game and records “snapshots” in its memory. The machine observes where the fingers start and stop, and how objects on the screen move according to each other, while also observing the game’s score for signs of progress. The robot then mimics the child’s movements when playing the game. It is programmed to “shake its head in disappointment” when the game’s objective is not achieved and to celebrate with a happy sound, a dance, and eyes lit up when a score is made.
Ayanna Howard, PhD, Georgia Tech, Motorola Foundation Professor in the School of Electrical and Computer Engineering, project leader, explains that the robot is able to learn by watching since it knows how the interaction with a tablet app is intended to work.
“It recognizes that a person touched here and ended there, then deciphers the information that is important and relevant to its progress,” Howard adds.
The robot is built to analyze the new information and provide appropriate social responses while changing its play strategy. A flexible design for end users, Hae Won Park, Howard’s postdoctoral fellow says, is one way to integrate robots into society.
“If a robot is only trained to perform a specific set of tasks and not able to learn and adapt to its owner or surroundings, its usefulness can become extremely limited,” Park says.
The flexibility, the release says, is why Howard and Park feel the “robot-smart tablet system” may serve as a future rehabilitation tool for children with cognitive and motor-skill disabilities. The program could potentially be programmed by a clinician in order to accommodate a child’s needs, including hand-eye coordination tasks and turn taking. The machine could then be sent home with the child, the release notes. To this end, the robot could allow for repetitive rehabilitation sessions with the child that might otherwise become tedious.
Howard provides an example in the release. If a child’s rehab calls for 100 arm movements in order to improve precise hand-coordination movements, “He or she must touch and swipe the tablet repeatedly, something that can be boring and monotonous after a while. But if a robotic friend needs help with the game, the child is more likely to take the time to teach it, even if it requires repeating the same instructions over and over again. The person’s desire to help their ‘friend’ can turn a 5-minute, bland exercise into a 30-minute session they enjoy.”
In their study, the release notes that Howard and Park asked grade-school children to play Angry Birds with an adult watching nearby. The children were then asked to teach a robot how to play the game. The researchers note that the children spent an average of 9 minutes with the game as an adult watched. They played a total of 26.5 minutes with the robot. They also interacted considerably more with the robot than the person, the release states. Additionally, 7% of the children’s session with an adult included eye contact, gestures, and talking. It was nearly 40% with the robot.
The study’s findings were also presented at the June Rehabilitation Engineering and Assistive Technology Society of North America (RESNA) 2014 Annual Conference.
According to the release, moving forward, the team will be including additional games for the robot and recruiting more children diagnosed with motor impairments and Autism Spectrum Disorder (ASD) to interact with the system.
The recent study included two children with ASD. The children’s interaction times with the adult were significantly less than those in the typically developing group and about the same with the robot.
[Source(s): Georgia Institute of Technology, Newswise]