Introducing the new Autom. This is a personal robot developed by Intuitive Automata, a spin-off of MIT alum (and fellow Breazeal alum) Cory Kidd. Based on Cory’s PhD thesis, it is a motivational robot designed to be a tool people can use in a weight loss regimen. Doctors have found that people who consciously keep track of food and exercise while dieting have more success. Through daily interactions, Autom helps people in this aspect of dieting. In a recent study, they compared groups of people using Autom to groups using similar desktop software and to people using pen and paper. The Autom group was found to stick to their diet twice as long as the other groups.
Autom’s new look (right) was unveiled last week at an entrepreneurial event in Barcelona. Looking good…congrats to everyone at IA!
Lead by my colleague Henrik Christensen, there has been an effort over the past year in the robotics community to define a “roadmap” for robotics research in the US. Supported by the Computing Community Consortium, four workshops were held that brought together representatives from industry and academia to outline the most fruitful research questions for the US to be pursuing. These discussions were centered on four focus areas: Manufacturing, Healthcare, Service Robots, and Emerging Technologies.
These discussions resulted in a concrete roadmap that outlines a research agenda for non-military robotics research. US funding agencies have a strong history of supporting research for military robotics, but there’s been very little funding available for non-military applications. So this is what Henrik and Co. went and told the congressional caucus on robotics on May 21st. They presented the roadmap and made the case for US research funding to be specifically allocated for non-military robotics through such agencies as the NSF, the NIH, and others.
In addition to the presentation, there was a demo session for congressional staffers. My student, Maya Cakmak took our interactive learning demonstration. So, our robots have been to Congress, cool!
It has been very exciting to be a part of the roadmap discussion, and we’re all looking forward to seeing what impact it might have on future funding initiatives for robotics.
We recently presented a paper in HRI 2009, “Learning about Objects from Human Teachers“. One of my PhD students, Maya Cakmak, did a nice study looking at how everyday people (well, your average college student anyway) try to teach our small little upper-torso robot, Junior, what he can do with a simple set of objects. Objects in the set have various “affordances,” for example, some things roll, others can be picked up, and a little box could be opened.
Our approach, Socially Guided Machine Learning, looks at ways that a human partner can intuitively help the robot learn. The paper details three main points:
1) We conducted experiments with Junior, and made six observations characterizing how people approached teaching about objects. For example, people start with simple objects and move to more complex ones. They structure the session in chunks focusing on one affordance at a time. And they lead the robot to significantly more positive experiences (where something happens) compared to non-social self exploration. This is particularly useful when an object’s affordance is a rare event (e.g., opening the lid of a box).
2) We showed that Junior successfully used transparency to mitigate errors. We showed that Junior could use eye gaze to communicate the need for help. And that people all interpreted this gesture and helped the robot in an appropriate way. This in turn significantly sped up the interaction.
3) Finally, we present the impact of “social” versus “non-social” data sets when training SVM classifiers. In particular, we see the impact of people’s propensity to focus on rare events. Classifiers trained with socially collected datasets are much better at predicting rare effects compared to non-social datasets.
The Pleo story is not over! This little dinosaur robot designed by UGOBE had lots of buzz (for over a year) before it came out, presenting at DEMO and other techno-elite venues. But a few months ago, the website disappeared and it looked like Pleo was done. But now Jetta Company Limited has acquired the assets of Ugobe and will re-launch the Pleo robot.
My lab worked with UGOBE under their academic partnerships program. They sent us a couple of Pleos and gave us early access to the Pleo Development Kit (PDK). It was a fun little platform to play around with, but ultimately didn’t quite have enough juice to be a compelling platform for our social learning and HRI research. Mainly because it was easy to script the robot, but not so easy to make it dynamic and interactive due to flaky sensors and limited on-board processing power. But for the price point, you can’t expect too too much.
What I hope they add in the next rev. is wireless control. I’d love to be able to easily control Pleos from our existing codebase for AI/HRI. Let’s see…
Rod Brooks recently gave a talk at Maker Faire, where he gave some motivation behind the new company he’s starting. No details at all on what kind of robot we’ll see from them, but a nice articulation of why the US needs robots in order to have any chance of staying competitive in the manufacturing domain.
The punchline: robots can allow the US worker to be more productive and cost-effective than outsourcing, which would drive manufacturing jobs back to the US. The main challenge here is that current robots in manufacturing (like the one pictured above) are big and dangerous, so people can’t safely work side-by-side with them. Thus we need a new class of robots that can safely work cooperatively with ordinary people. Robots can do mundane tasks leaving people to do the more skilled tasks.
This is a great challenge problem, one that I’ve been thinking about recently as well, since it is an excellent example of a real application where Human-Robot Interaction is a key factor in determining the robot’s success. Very exciting that Rod is aiming his star power at this domain.
Congrats to the folks at Willow Garage, they’ve announced that PR2 passed it’s second milestone (opening doors, and plugging itself into power outlets). I got to see individual demos of the door opening and outlet plugging when I visited their lab in March. So, great to see the progress on integration and robustness.
Hope this means we’ll soon see the call for proposals for the PR2’s that WG is going to be sending out into the world!
Lead by my colleague 
The 
