Maja Mataric´ is a professor of Computer Science, Neuroscience, and Pediatrics at the University of Southern California, founding director of the USC Center for Robotics and Embedded Systems, co-director of the USC Robotics Research Lab and Vice Dean for Research in the USC Viterbi School of Engineering. She received her PhD in Computer Science and Artificial Intelligence from MIT in 1994, MS in Computer Science from MIT in 1990, and BS in Computer Science from the University of Kansas in 1987. She is a Fellow of the American Association for the Advancement of Science (AAAS), Fellow of the IEEE, and recipient of the Presidential Awards for Excellence in Science, Mathematics & Engineering Mentoring (PAESMEM), the Okawa Foundation Award, NSF Career Award, the MIT TR100 Innovation Award, and the IEEE Robotics and Automation Society Early Career Award. She served as the elected president of the USC faculty and the Academic Senate. At USC she has been awarded the Viterbi School of Engineering Service Award and Junior Research Award, the Provost’s Center for Interdisciplinary Research Fellowship, the Mellon Mentoring Award, the Academic Senate Distinguished Faculty Service Award, and a Remarkable Woman Award. She is featured in the science documentary movie “Me & Isaac Newton”, in The New Yorker (“Robots that Care” by Jerome Groopman, 2009), Popular Science (“The New Face of Autism Therapy”, 2010), the IEEE Spectrum (“Caregiver Robots”, 2010), and is one of the LA Times Magazine 2010 Visionaries. More details here.
The recently released movie “Robot & Frank” features an elderly, and quite curmudgeonly, thief named Frank, whose family provides a caregiving robot to take care of his needs. The robot’s capabilities in the movie are well beyond the current engineering state of the art, but, ironically, most people won’t find the robot unrealistic (though it is), but they may find the bond that forms between the robot and Frank hard to believe (yet it is realistic according to latest research).
There is a popular misconception that people, especially older people, do not like robots. In the movie, against his own stated wishes and beliefs, Frank becomes attached to the robot and their joint activities and shared secrets. Is such a scenario possible? The answer, based on human-robot interaction (HRI) research today, is already “yes”, even without the sophisticated technology which the robot in the movie features, though such technology is under development.
Robotics research is increasingly turning to the challenges of HRI inherent in the myriad of robotics applications that are coming in the next few decades. These include robotics technologies for caregiving of end-user populations which include the elderly aging-in-place (i.e., living in their homes as long as possible), those ageing in institutions, as well as stroke patients, children with autism, and other social and developmental disorders, and many others.
What do these very different populations have in common? All require customized one-on-one care for many hours per day which is already lacking for most, and is growing increasingly so with rising instance rates of diseases and disorders and the growth of the aging population. While safe, trained, and affordable human care is always best, when such care is impossible to get, safe, trained, and affordable technology has the potential to fill the growing gap.
My Interaction Lab’s research at the University of Southern California defined the field of socially assistive robotics (SAR), the research into the development of robots capable of helping people through social rather than physical interaction. To date, we have explored socially assistive robots for providing rehabilitation for stroke patients, children with autism, Alzheimer’s patients, and exercise for healthy elderly. One aspect of our research focuses on understanding how the robot’s embodiment, the fact that it is a physical entity co-present with the user, influences the interaction when no physical interaction is involved. A growing body of research shows that people engage more, respond better, and sustain the influence of physical robots over non-physical agents (e.g., computer or cell phone simulations). A weight loss study showed that participants using a simple robot were more motivated to lose weight then those using a computer agent or a standard notebook method [Kidd]. Another study found that elderly residents in a retirement home showed no significant preference for a live dog over a robot dog (a Sony Aibo). In a recent study we performed with 66 adults, 33 of whom were over 65, we found a strong statistically significant preference for a robot coach over a computer agent coach with identical appearance and capabilities. Most interestingly, the older participants had a stronger preference for the robot, exactly countering the popular misconception about older people and robots. Such evidence is mounting.
We are interested in what causes these effects, but that is likely a neuroscience study. In the meantime, we are studying when these effects appear and how we may leverage them to create more effective robot caregivers, through the use of appropriate body language, expressions, relational and functional properties of the robot. We are exploring methods for motivating people through social interaction involving speech, gesture, embodied games, and any other social tools available to the robot, in all cases without any physical work or contact with the user. We impose the non-contact constraint for both safety and affordability: robots that can manipulate objects in the real world need both sophisticated sensing and effectors (arms, hands, fingers/grippers), and the associated hardware in the form of motors and batteries. The former require higher cost, the latter require weight and thus reduced safety. Since our interest is in socially assistive, affordable, and safe systems, we stay away from physical contact. However, there is also a great deal of interesting and challenging research in touch and manipulation; researchers are working on smaller, lighter, safer and more affordable robot bodies.
It is interesting to contemplate, and important to prepare for, the not-so-distant future that will feature the convergence of various technologies, including mobile apps and agents, aware homes, and personalized socially assistive robots, all aiming to improve human quality of life.