I'm intrigued by several recent high-tech robot toys that provide an immersive, augmented-reality experience that is grounded in a real, physical robot.  Almost universally, these new toys are controlled by smart phones or tablet computers (eg. iPad / iPhone / iPodTouch or Android devices) and will likely be hacker / developer friendly.  They are becoming increasingly sensor-rich and often offer video feedback -- all enabled by the commoditization of robotic components.  For example, the Parrot AR.Drone is a quadrotor helicopter that enables UAV aerial dogfights.  Another is the forthcoming Orbotix Sphero, a simple robot ball that will presumably support many mini-games: like a real-life version of Super Monkey Ball or the best cat toy ever!  Yet another example for you hackers out there, Matt Might created an iPhone-based multitouch remote control for a Scribbler robot in just 6 hours and 200 lines of JavaScript / Python!

I would like to introduce you to iRobot's latest prototype: a new telepresence robot named AVA that was unveiled this week at the Consumer Electronics Show (CES 2011) -- see the video below.  Through AVA, iRobot intends to explicitly leverage the proliferation of tablets / smart phones and their associated app stores.  They intend to furnish actuation (mobile base, pan-tilt unit, telescoping linear actuator spine, etc.), a sensor suite (including sonar, laser, and a depth camera like Microsoft's Kinect), and basic robot software (eg. obstacle avoidance, mapping, and direct physical interfaces).  Meanwhile, you provide the brains in the form of a tablet (eg. iPad or Android).  In theory, this should open up mobile robot application development to a much broader audience, creating the oft-discussed robot app store.  When combined with the recent announcement of the Scooba 230 floor cleaning robot (which I will certainly purchase), I would say iRobot is still innovating!

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.

Electrotactile arrays are a lesser-known form of human-machine interface (HMI) that apply electric current to skin-contacting surface electrodes to excite cutaneous nerves and give the illusion of texture, pressure, or pinpricks (depending on current strength and electrode resolution) all without mechanical vibration.  This technique has been around for many years for:  non-visual fighter pilot status displays, tongue interfaces, surgery guides, and for forehead-mounted camera displays for the blind.  Enough background... The exciting news is a recent product developed by Senseg and Toshiba Information Systems called "E-Sense" that successfully embeds an electrotactile display into a touchpad, LCD, or other curved surface (eg. all over a cellphone), thereby providing programmable high-resolution texture feedback to a user -- see the video embedded below.  I would wager that this feedback could greatly enhance haptic shared awareness in teleoperation / telemanipulation systems.

This new humanoid robot named "Cody" comes from Georgia Tech's Healthcare Robotics Lab (to which I belong).  Cody is composed of a Segway RMP 50 Omni mobile base, 1-DoF vertical linear actuator, and a pair of 7-DoF Meka Arms with series elastic actuators (the same as Simon).  This mobile manipulator has shown some pretty impressive capabilities.  It can open doors, drawers, and cabinets using equilibrium point controllers developed by Advait Jain and Prof. Charlie Kemp.  It also has a nice direct physical interface (touching interface) to reposition the robot that was developed by Tiffany Chen and Prof. Charlie Kemp. Much of the code controlling this robot is open-source and has ROS (Robot Operating System) interfaces.  Be sure to check out the videos and photos below.

Colleague and labmate, Tiffany Chen, pointed out an interesting new robot named "MeBot" from MIT's Personal Robotics Group.  Later this week, MeBot will be presented at the conference on Human-Robot Interaction (HRI 2010) in Osaka, Japan.  The associated paper, "MeBot: A Robotic Platform for Socially Embodied Presence," has been nominated for best paper.  In a nutshell, MeBot is a semi-autonomous robotic avatar that provides rich, remote interaction by conveying non-verbal channels of social communication in addition to video, something that is not provided by existing phone and video conferencing.  The expressiveness of MeBot is impressive.  It reminds me of the (now well-known) CrabFu Swashbot, but ups the ante by including video capabilities.  Be sure to check out the videos and photos below to see what I mean.

Following up on last week's article about building robot hands with compliant under-actuated fingers, I'd like to examine a technique to build aesthetic shells for robot heads using a combination of 3D-printed master forms, silicone molds, and quick-setting plastic final products.  The technique examined was used by MIT alum Cory Kidd to build 18 prototypes of the Autom weight-loss coach for his PhD dissertation, a product that is being continuously refined at Cory's new startup, Intuitive Automata.  This technique seems a bit involved; I probably would have just outsourced a full 3D printed ABS version of the head, especially since there were 18 of them.  However, I always find these advanced robot fabrication techniques enlightening.

With micro / pico projectors being sold for under $250, and robot toy maker Wowwee getting in the game, it was only a matter of time before projectors would be found on robots -- especially since the general concept dates back at least three decades to R2D2's holographic projections in the original Star Wars trilogy.  In fact, Hizook previously examined a number of robots with projectors used to communicate intention.   Following the development of a laser pointer interface by the Healthcare Robotics Lab (to which I belong), myself and numerous labmates ruminated about the marrying of these two technologies -- it seemed a natural extension of the "Clickable World", wherein the world is composed of virtual buttons or icons selected via a laser pointer analogous to a PC mouse, to include visual feedback via an on-robot projector.  It seems ideas rarely stand in isolation; I'm now aware of two robotic systems that use both video projectors and laser pointer interfaces.  The first is a very preliminary "late breaking results" submission to HRI 2009, while the other is a fully-realized system developed in JST's ERATO program.  The latter research happens to have a compelling video, embedded below.

We've seen robots controlled with projector interfaces and laser-pointer interfaces, and now we can add tabletop interfaces to the list.  My labmate, Hai Nguyen, pointed out the CRISTAL project from the Media Interaction Lab at the Upper Austria University of Applied Sciences.  The CRYSTAL project is an interesting "smart home" technology that uses a tabletop interface (similar to Microsoft's Surface) and a ceiling-mounted camera to display and control household electronics such as lights, TVs, digital picture frames, and robots!  To command the robot, the user "draws" the desired robot path on the tabletop computer using their finger.  The robot then follows the route via optical tracking through the ceiling-mounted camera. Interesting interaction, and its always good to see robots become sufficiently ubiquitous that they're classified (and controlled) in the same manner as other home electronics.  Check out a video of the interaction below.

Dr. Andrea Thomaz of Georgia Tech's Socially Intelligent Machines Lab was recently awarded the prestigious "MIT Tech Review 2009 Young Innovators Under 35", an honor shared with last year's robotics recipient, Andrew Ng.  Simultaneous to this fantastic news, Andrea's lab unveiled an amazing new robot named Simon (see photos and videos below).  Simon features an articulated torso, dual 7-DOF arms, and anthropomorphic hands from Meka Robotics along with an expressive head designed at Georgia Tech.  Simon is designed to study human-robot interaction from a social learning vantage, such as learning by demonstration and human-robot collaboration.  I'm very enthralled for Andrea, and I'm proud to have taken her graduate research course on human-robot interaction while at Georgia Tech. 

The iconic Pixar animated lamp, Luxo Jr., unofficially debuted in animatronic form at Disney's Hollywood Studios in late June (videos below).  Both the animated and animatronic Luxo Jrs. have remarkable anthropomorphic emotive capabilities in spite of their simple, non-human form.  This reminds me of conversations in Dr. Andrea Thomaz's human-robot interaction course about applying animation techniques to design more effective social robots -- clearly Disney's Imagineers have perfected this art.

Describing science as "beautiful" makes perfect sense to me; I believe the physics experiments described in The Prism and the Pendulum are on par with the greatest paintings and sculptures ever conceived!   However, I'm having difficulties classifying the $30,000 robot, Keepon:  Is it a research robot, an art-robot, or both?  On one hand, there is evidence supporting its role in important robotics research.  On the other hand, there are the numerous (many more?) whimsical videos of Keepon dancing to music or traveling the world, such as the "Keepon Goes Seoul-Searching" video to be shown on Friday at the Human-Robot Interaction (HRI) 2009 conference (we show this video below).  Having seen Keepon in person, I can attest to its "cuteness" factor and quality design... but my questions are: "Where is the line between art and research drawn?"  "Does such a line, necessarily, exist?" and "How can HRI researchers and peer-reviewers objectively evaluate important robotics research that also possesses strong artistic components?"  I'd love to hear your thoughts.

Back in May 2008 it was announced that CMU professors Sara Kiesler and Jodi Forlizzi (from the HCI Institute) and Paul Rybski (from the Robotics Institute) were awarded $500k in Microsoft's Human-Robot Interaction funding to develop a social, snack-selling robot to traverse Newell-Simon and Wean halls (press release).  After seeing a prototype appear on Flickr in July, we've all been waiting patiently to see pictures of the final version.  Well, the wait is over -- photos of the new CMU snackbot, conceptual designs, and construction photos are contained below!  It appears that the CMU team is progressing nicely.

The folks at Dr. Matsumaru's Bio-Robotics & Human-Mechatronics Laboratory have worked on some very interesting human-robot interaction projects.  I'm particularly interested in their video-projector interfaces.  In one scenario, the video projector shows the robot's intended motion trajectory.  In another scenario, dubbed the "Step-On Interface" or SOI, users step on projected "buttons" to control the robot.  According to videos (below), Dr. Matsumaru is targeting home-based service robots.  Read on for videos and more information about the video projector robot interfaces, as well as some others (using visible lasers, LCDs, and Persistence of Vision or POV displays).

There has been a lot of press in the last six months revolving around El-E, the autonomous mobile manipulation platform for the motor impaired out of Georgia Tech's Healthcare Robotics Lab (to which I belong).  There was a report in the NY Times on El-E's laser-pointer interface, and now a report in MIT Tech Review on El-E behaving like a service dog.  Recently, the lab's director (and my advisor) Dr. Charlie Kemp, gave an impressive talk at Carnegie Mellon's Robotics Institute (CMU-RI) where he adeptly ties together these research initiatives and makes a compelling case for more autonomous mobile manipulators for the motor impaired.  Read on for the CMU-RI video and some choice images and themes from the talk.

OK, I know what everyone is thinking... "What is this craziness? Inter-Galactic Love?" Well, let's just attribute it to a poor Japanese-English translation -- the title should have been left at just "Hinokio," which is a play on words from the old, classic film title "Pinocchio."  In my opinion, this is the second-best robot movie of all time in terms of robot realism and "cool" humanoid robots (second to I-Robot), though it does posses some of those cheesy Japanese memes.  The movie is about a Japanese boy who is unable to walk and thus uses a telepresence, humanoid robot to experience life; everything the robot sees, hears, and feels, so does the boy. The film has amazing graphics and cinematography, and the human-robot interaction techniques are very well thought-out. I'd recommend everyone grab a copy and watch it; it's definitely worth the time. Read further for more detailed information and some very cool images from the film.