I think this is both brilliant and hilarious... University of Delaware researchers, James Galloway and Sunil Agrawal, were awarded a two-year, $325k NSF grant to explore robot-enabled mobility for special needs children, with the goal of spurring cognitive development -- this is brilliant. However, why focus solely on special needs children? I think it is hilarious to imagine "regular" children using "smart wheelchairs" to putter around before they learn to crawl / walk -- it would certainly make for some entertaining rounds of baby-bumper-cars! Adding to the hilarity, their initial prototypes are Pioneer robots pulling a plywood trailer, supported by casters, with a small chair atop (images below)! But who am I to judge... we can all relate to "ugly prototype syndrome."
First, let's look at the prototype:
(Images credit: Kathy Atkinson, UD)
Like I said, I can just imagine the insane games of baby-bumper-cars during daycare. Good thing a remote teleoperator can override (at least, so it appears from the image below left). Of course, the prototype is just meant to research the concept (or garner additional funding); the image from PhysOrg is more telling of the researchers' intentions.
From the University of Delaware press release:
Currently, infants who cannot walk due to severe brain, muscle and/or bone disorders must wait until they are three years of age, if not much older, before a power wheelchair is available to them. The research team hopes to make mobility available at a much younger age.
And from PhysOrg:
Children with mobility issues, like cerebral palsy and spina bifida, can't explore the world like other babies, because they can't crawl or walk. Infant development emerges from the thousands of daily discoveries experienced by babies as they move and explore their worlds.
As an aside, I will be curious to see what sort of autonomy and reasoning is added to these robotic powered wheelchairs. Obviously, there must be some obstacle avoidance (stairs!). More provocatively, I'd be curious to see what sort of conclusions can be drawn about cognitive development (normal versus impaired), and if the data collected could provide really interesting insights to an infants' motivations (the classic "exploration versus exploitation" question from machine learning).