Assistive robots that autonomously manipulate objects within everyday settings have the potential to improve the lives of the elderly, injured, and disabled. Although researchers have demonstrated relevant capabilities within laboratory environments, current methods are untested and potentially unsuitable for the variability of real-world healthcare environments. In order to address this critical issue, the new infrastructure funded by this award consists of a state-of-the-art robot (a mobile manipulator) dedicated to research conducted outside of the lab via collaborations with healthcare researchers and providers. The robot spends extended periods of time (residencies) in environments where assistive robots are expected to make a positive impact, including the homes of persons with disabilities, assisted living environments for the elderly, and clinical facilities. These residencies enable robotics researchers to maximize the impact of their research by identifying and addressing the roadblocks to deployment of autonomous mobile manipulators for healthcare. The research supported by this infrastructure will result in new methods for assistive manipulation and contributions to compliant arm control, multi-modal perception, and human-robot interaction. It will also begin to quantitatively characterize the variability of real-world healthcare environments. Results of this research will be communicated via academic publications, a website, open source code, and publicly released data captured with the robot. The robot will also have residencies at Spelman College (an HBCU for women) to promote science, technology, engineering, and mathematics (STEM) education.
Millions of people require physical assistance on a daily basis due to disabilities resulting from illnesses, injuries, aging, and other causes. Mobile robots with autonomous capabilities have the potential to provide 24/7 personalized care, dramatically improving the quality of life of people with disabilities. Real-world success for this type of robot presents numerous challenges. This award has supported research that seeks to enable mobile robots to provide physical assistance in real human environments, such as people’s homes. Specifically, this award funded the purchase of a PR2 robot and associated equipment for use by the Healthcare Robotics Lab at Georgia Tech directed by Prof. Charlie Kemp. This infrastructure has supported highly-successful collaborative research efforts that have tangibly moved the field forward. Notably, this infrastructure helped support a collaboration between the Healthcare Robotics Lab, Willow Garage, and Henry & Jane Evans named the Robots for Humanity project. This project has shown the feasibility of human-scale mobile robots (mobile manipulators) for in-home assistance. Henry Evans has severe motor impairments due to a brainstem stroke. Through this research effort, Henry has been able to perform a number of tasks for himself in his home for the first time in 10 years, such as pulling a blanket over himself, shaving himself, and operating household mechanisms, like drawers and doors (see pictures). A key aspect of this research has been giving robots the ability to intelligently regulate the forces they apply while providing assistance. This infrastructure has also helped support a collaboration between the Healthcare Robotics Lab and the Human Factors and Aging Lab at Georgia Tech, which is directed by Prof. Wendy Rogers. This collaboration has focused on research to better understand how mobile manipulators can benefit older adults. This effort has included studies during which older adults from the Atlanta area interacted with the PR2 in the Aware Home, which is a freestanding house on the Georgia Tech campus for research on in-home technologies. Among other results, these investigations found that older adults are open to receiving assistance from mobile manipulators like the PR2 and would even prefer robot assistance to human assistance for some tasks (see picture). The research supported by this infrastructure has resulted in new methods for assistive robot manipulation and contributions to compliant arm control, multimodal perception, and human-robot interaction. It has also resulted in the quantitative characterization of the forces associated with everyday assistive tasks, such as shaving, wiping, and door opening. The robotic systems developed as part of this research blend the capabilities of the person receiving care and a semi-autonomous mobile robot. This research has demonstrated that mobile manipulators can assist people in a wide variety of tasks in the real world, such as object retrieval, operating household devices, shaving, and scratching. It has also shown that mobile manipulators can help a person in distinct surroundings, including when the person is in a wheelchair or in bed, and can do so in the person’s actual home. In addition, this work has resulted in numerous peer-reviewed publications, as well as open source software and open hardware, which the Healthcare Robotics Lab has released to the public under liberal open source licenses. This infrastructure has also helped support education by serving as a resource for class projects at Georgia Tech, providing material for an undergraduate class at Georgia Tech, helping with the training of undergraduate and graduate students, and being used for compelling demonstrations during tours by undergraduates from Spelman College and Atlanta area K-12 students.
