A few weeks ago, my labmates from Georgia Tech's Healthcare Robotics Lab presented a paper at IROS 2010 entitled, "Towards an Assistive Robot that Autonomously Performs Bed Baths for Patient Hygiene." Their work used Cody, a robot with compliant arms, and a specialized "bath mitt" end effector to perform wiping motions that could clean selected areas of an actual person's body, including the upper arm, forearm, thigh, and leg. In this robotic cleaning task, the robot initiated and actively made contact with a human. The psychological impact of such robot-initiated contact is an interesting question -- one I believe will be important for future healthcare and human-robot interaction (HRI) tasks. Read on for a video and discussion by the authors.
This work was performed by members of my lab, the Georgia Tech Healthcare Robotics Lab: Dr. Chih Hung King (postdoc), Tiffany Chen (PhD student), Advait Jain (PhD student), and lead researcher Dr. Charles C. Kemp (lab principle investigator). This is what Chih Hung King, the sole subject in the study, had to say about the work:
We developed an autonomous behavior that allows Cody, a robot with compliant arms, to perform wiping motions that clean debris from human skin, making progress toward autonomous robot bed baths for patient hygiene. A laser-based selection interface enables an operator to select an area of skin, after which the robot autonomously performs a wiping motion using equilibrium point control to clean the selected area. We tested the performance of the cleaning behavior by commanding the robot to wipe off a 1-inch2 area of debris placed on the surface of the upper arm, forearm, thigh, and leg of a live human subject: me, in both the paper and video.
As the sole subject in this initial experiment, I'd like to share my impressions of the interaction. In the beginning I felt a bit tense, but never scared. As the experiment progressed, my trust in the robot grew and my tension waned. Throughout the experiment, I suffered little-to-no discomfort.
The tasks performed in this experiment involved the robot initiating and actively making contact with a human. This differs from most (current) research on human-robot contact, which is initiated by humans rather than robots. It would be interesting to study how the general population, specifically patients, would react to such robot-initiated contact. Indeed, the psychological impact of robot-initiated contact may become important for future human-robot interaction (HRI) research.
Here is a closer look at the wiping behavior from the paper:
Now, I understand that it is easy to poke-fun or jest about robot-human contact -- I've done my fair share, and it has even entered the mainstream media (ie. Big Bang Theory). However, as anyone who has ever dealt with an incapacitated loved one can attest, bed baths are one of the least unpleasant / awkward tasks befalling caregivers and family members. Presumably robots could one day fulfill such hygiene tasks and offer many benefits: increased privacy and comfort, greater independence and quality of life, consistent performance, and long-term operation. I think this is a step in the right direction.