Go-Robo programming software control for WowWee robots

Haven’t you always wished that it should be easier to program your favorite WowWee robot in some better way other than using the remote control? Q4Technologies is here to make your dreams a reality. They are currently beta testing the Go-Robo development suite for programming any of WowWee’s Robosapien, RS Media, Robopet, Roboreptile and Roboraptor entertainment robots.

Go-Robo supports programming using two methods. A graphical method allowing younger learners to describe complex behaviors using simple graphical blocks similar to the programming environment for Lego’s Mindstorms NXT robot.

More advanced users can program their WowWee robot using the more advanced Go-Robo ID script (GRIDscript) language. According to Q4Technologies,

GRIDscript uses a simple and consistent syntax based on modern commercial practices. At the upper end, there is no limit to GRIDscript. It contains all the mathematical functions of proper commercial and scientific programming languages. And beyond this technical experts can show their prowess by hacking the XML databases; this may include creating your own custom instructions, translating the commands to French or German, or adjusting the command timings.

All of this sounds very exciting, although, I have to admit that some of the statements about Go-Robo’s abilities might be a bit exaggerated. That said, the software is being beta tested until March 2007 and it will be available for purchase after that. If you are interested in beta testing Go-Robo then you can contact Q4Technologies here.

As far as I am concerned, I will wait until the RS Media robot is available for sale in North America at which point I will consider testing Go-Robo. Until then, if any of you are participating in the beta testing program and would like to tell me your opinion about Go-Robo, I am all ears!

Honda UK ASIMO warm technology ad

Honda’s United Kingdom branch has been showing during the holiday season a new TV ad featuring Honda’s advanced humanoid robot ASIMO. The goal of the new ad campaign is to create a feeling among viewers that this new technology is approachable and warm. During the 90 minute spot, ASIMO is seen navigating around a science museum on a journey of discovery. Some of the highlights include ASIMO looking through a telescope and pausing to look at its own reflection on a TV screen. I have to admit that this ad is successful in creating a warm feeling towards humanoid robots and related technologies. It is wonderfully done and a pleasure to watch truthful to Honda’s tradition of creating engaging TV ads.

Japan announces winners of the first Robot Awards

Earlier today and during a lavish ceremony, Japan announced the winners for the first government sponsored Robot Awards. Among the winners include the My Spoon robot for feeding the disabled and elderly and Paro the therapeutic seal robot. My Spoon is currently sold in Japan and Europe while at least 800 Paro robots are used for therapy in Japanese nursing homes and by autistic handicapped children. Ten robots received an award out the 152 that were nominated. A third winner worth mentioning is an automatic vacuum cleaner for industrial applications developed by Fuji Heavy Industries. The robot is much larger than your average Roomba and it is capable of moving between floors using the elevator.

Japan is emphasizing and funding research and development in robotics in order to care for a rapidly aging population and a shortage of workers. In fact, it is expected that Japan’s population will decrease by 30 percent by 2055 with 40 percent of the people aged 65 or older. Of course there is an obvious solution to Japan’s labor problems and that is to allow foreign workers to enter the country but there is a general disinclination towards such a policy.

Ookles wants to automatically organize your photos

Ookles is a new Web company that will officially launch early next year (2007) with the hope to help people organize their digital photos using machine vision technologies. Ookles wants to be a website similar to the very popular Flickr. However, its founders want to automate the semantic labeling and categorization of user photos taking advantage of recent advances in machine vision algorithms. Currently, there is little information available about how Ookles is supposed to work, however, Michael Arrington (TechCrunch) was privileged to an early look. He briefly explains how Ookles uses supervised learning to find photos of the same person using face recognition.

Like Riya, Ookles will find and show thumbnails of faces from photos, and then analyze that face against other faces in your photos. You tell Ookles which ones are a match. Ookles repeats the process a couple of times until it has a good idea of who the person is. It will then tag all photos with the name, and future photos containing that person will also be auto-tagged. The demo worked perfectly - it took a few steps to train it and then all photos were properly tagged.

Arrington also discusses a feature that enables Ookles to group similar photos together into albums. Ookles hopes to use object recognition techniques to automatically label a user’s digital photos. How well this will work compared to human tagging is not known but I don’t expect it to be as good. In fact, I would not be surprised if the early version of Ookles simply suggests tags which the user could use for each photo.

Finding ways to automatically categorize the large number of digital photos available online is certainly a worthy cause. To my knowledge, however, even state of the art machine vision algorithms are not currently capable of doing this. It will be interesting to track the progress of Ookles during 2007 and hopefully very soon any one of us will be able to try out their system.

WowWee's Dragonfly wing-flapping robot video

WowWee are well known for the Robosapien and Roboreptile line of remote controlled robot toys but apparently they have been busy working on something new and really cool. While we, in North America, are still waiting to get our hands on the RS Media version of Robosapien, WowWee FlyTech has been developing a tiny flying robot with a twist. The robot mimics a Dragonfly in appearance and it actually flaps its wings in order to fly. This could be the first ever robot to fly using this approach, at least as far as I know. The question anyone would ask is whether the Dragonfly can actually fly and how well. The guys at T3 got an early look at the new robot and they tell us that the robot works well and as advertised. In fact, it can stay airborne for a good 15 minutes. Best of all, they have a video showing the robot in action and I have to admit that it looks amazing. Check it out,

PS: I realize that a remote controlled toy hardly qualifies as a robot but I have faith that WowWee will eventually be enabling the Dragonfly with some artificial intelligence capabilities such as avoiding obstacles and maybe flying by itself. Getting the robot to fly is a huge first step.

Microsoft Robotics Studio Release 1.0 available for download

Earlier this week, Microsoft's robotics group officially released version 1.0 of the Microsoft Robotics Studio, a new robot development environment. Microsoft Robotics Studio is free for non-commercial use. It costs $399 for a commercial use license.

The software allows novice users to develop robotics software using a drag-and-drop interface. Advanced users with programming skills can write low level code using Microsoft's Visual Studio as well as Visual C# and Visual Basic. The software comes bundled with the PhysX engine from AGEIA for developing robots in a physics-based virtual environment.

Microsoft Robotics Studio is aimed at both the amateur and professional developers. Microsoft has made a huge effort to lobby their development environment to robot manufacturers and as of this writing at least 30 of them have announced support for it. Some partners include iRobot, makers of Roomba, White Box Robotics, makers of the PC-BOT, SRI International and LEGO Systems, makers of the very popular Mindstorms NXT robotics toolkit. In addition, Microsoft Robotics Studio has been welcomed by the robotics groups at Georgia Tech and Carnegie Mellon University.

The official release of Microsoft Robotics Studio probably spells bad news for Evolution Robotics who has had a similar product in the market for quite some time. I am glad that Microsoft is entering the robotics scene although I am not particularly happy that their development suit only supports Microsoft’s Operating Systems. Of course there is always the open source alternative Player/Stage platform.

You can download your copy of Microsoft Robotics Studio here.

CMU's TK60 symposium to honor Takeo Kanade on his 60th birthday

Carnegie Mellon University (CMU) will organize a special symposium titled "Celebrating Kanade’s Vision." The event known as the TK60 symposium is centered on Robotics Institute’s Professor Takeo Kanade and it is meant to honor him for his contributions to computer vision and robotics in the last 30+ years. The symposium will take place in Pittsburgh on March 8th and 9th 2007.

Throughout his career, Takeo Kanade, U.A. and Helen Whitaker University Professor, has collaborated with researchers and students from a variety of scientific disciplines who are honoring him with this symposium on the occasion of his 60th birthday.

Some of Takeo Kanade's most notable contributions include his work on face recognition, multi-baseline and real-time stereo vision, video surveillance and monitoring (VSAM,) robot manipulators (CMU DD Arm I) and virtualized reality. In fact, one of his most well known projects is the "Eye Vision" system that he developed for CBS and it was used to create breathtaking, matrix-like replays of the action during the broadcast of Super Bowl XXXV in 2001.

The symposium will include a number of invited talks. Some notable speakers include Tomaso Poggio (MIT) and Harry Shum (Microsoft Research) among many others. A special Distinguished Lecture from President Yuichiro Anzai of Keio University will kick-start the event on the morning of March 8th.

Raja Chatila interviewed on the Talking Robots Podcast

Dr. Raja Chatila was interviewed last week on the Talking Robots Podcast broadcast from the Laboratory of Intelligent Systems, EPFL, Switzerland. During the interview, Dr. Chatila gave a good high level overview of the current state of the art in robot navigation including the Simultaneous Localization and Mapping (SLAM) problem. He describes in a very clear way why navigation for robots is a hard problem whether it is on Earth or another planet. Dr. Chatila has many years of experience working with mobile robots and he is currently involved in the European COGNIRON project to concerned with the development of assistant and companion robots. He is also interested in the construction of planetary rovers.

Interesting tidbit from the interview: Would you think that robot navigation is easier on Earth or on another planet? The answer to this question might surprise you. Listen carefully to the Podcast to find out!

ASIMO falls down a flight of stairs during a live demonstration

Honda’s humanoid robot ASIMO was a victim of its own showboating as it fell down a flight of stairs during a live demonstration. ASIMO was on the 3rd step going up the stairs when apparently a mechanical failure seized its motors. The result was ASIMO falling back down the stairs hitting the ground. The robot continued to talk as it remained motionless on the floor describing how its foot sensors allowed the detection of stairs for safe navigation as demonstrated partially by ASIMO climbing the stairs while looking towards the crowd.

If anything this accident simply demonstrates how far away we are from constructing useful humanoid robots. ASIMO could not get up after the fall and it seemed oblivious to its own predicament as it continued to play back a given demo script. I love what Honda has done with ASIMO but I never believed the hype about how advanced it is since it has only be shown to operate in well constructed environments; and even in those occasions the probability for catastrophic failure is still very high as this video demonstrates.

Watch the video and draw your own conclusions. Be advised that the footage might be shocking to some.

The week in robotics (Dec 4th-Dec 19th, 2006)

I have been very busy this week so I was not able to post very often. However, here is a brief overview of what happened in the world of robotics and artificial intelligence for the second week of December 2006.

DARPA increased the prize money for teams participating in the Urban Challenge. Specifically, the top team completing the course will now receive $2 million, the second team $1 million and the 3rd team $500,000. In addition, the 78 teams competing without government funding will not receive separate award money but compete for the top 3 prizes along with the 11 teams receiving DARPA’s financial support. The announcement for prize money is good news for the teams because earlier this year DARPA had said that they won’t be able to pay the prize money originally announced because of a law prohibiting DARPA from distributing such money.

K-team introduced the 3rd update to their Kephera mini-robot platform. The Kephera III is built around the KoreBot system and it comes equipped with multiple sensor arrays including sonar, infrared and vision. The robot is small and well suited for experimentation in swarm robotics. It is also a beautiful platform for educational or home use. Kephera III runs Linux and it is programmable using the GNU C/C++ cross-compiler making it easy to port existing libraries for use with this platform. Taking advantage of the KoreBot board, Kephera III is easily upgradeable with Compact Flash extension cards and additional storage space.

Finally, on the lighter side of things, robots demonstrated their bartending skills at the Roboexotica Festival in Vienna. Wired News has good coverage of the event describing a number of the robots in display including Robert Martin’s Robomoji and David Calkins’s Chapok, the only robot to have somewhat humanoid form.

David Gelernter vs. Ray Kurzweil on Creativity: the mind, machines, and mathematics

In celebration of the 70th anniversary since Alan Turing’s seminal paper "On Computable Numbers" MIT held a public lecture featuring a debate between David Gelernter and Ray Kurzweil moderated by Rodney Brooks. The debate was about whether a machine could ever be conscious.

First and most importantly, you can watch the debate online here. You will need RealPlayer to view the video but luckily the software is freely available for all popular computer platforms.

In terms of the debate, I have to admit that it was mind blowing. I have been trying to create intelligent robots for almost a decade now and, honestly, I never thought about whether such machines would actually be conscious like a human being. My goal has been to build machines that can do jobs that are either impossible or too dangerous to be done by people. So, if I can send a robot to Mars to build a base for a human colony then who cares if the machine is conscious or not. But, one has to wonder, would it be?

And that is basically why there is a debate about it.

Ray claims that since computers are doubling in speed every year and our understanding of how the human brain is also increasing at the same rate, in just another couple of decades, we will be able to simulate the brain with a computer. When we do that, consciousness will emerge.

David says that consciousness is not a function of the brain but the entire body (including the brain of course.) So, one would have to simulate the entire body before the question of consciousness could be answered. "It's clear that you don't just think with your brain," he said. "You think with your body." Furthermore, he claims that a piece of software executed on a digital computer even if it is a simulation of the brain cannot be conscious since at the end of the day it is just executing a set of instructions. Finally, he claims that the notion of emergence is basically bogus; consciousness is about mental states that must exist or be created somehow within the brain; running a simulation of the brain would not create these mental states but simply model the process. "You can simulate a rainstorm and nobody gets wet," he said. Then Ray countered with "if you simulate creativity, then you will get real ideas out."

Ray and David didn’t agree on many things although at some point they did agree that they use different definitions for consciousness making difficult to have a meaningful debate in the first place.

This lecture is definitely worth watching. I know I didn’t understand everything they talked about and I will be watching it one more time.

The evolution of games versus that of robots

Marshall Brain recently posted on his Robotic Nation Evidence blog a video showing the evolution of games in the last 25 years. The video is great and you should watch it if you haven’t seen it yet. Surprisingly, Marshall makes the following bold claim,

All of that evolution has occurred in about 25 years. Robots will be evolving that quickly over the next 25 years.

I would like to argue that he is in fact wrong and there is absolutely no parallel that can be drawn between the evolution of games and robots.

In my opinion, he is comparing apples and oranges. When it comes to games and especially computer games, we already know the basic mathematics for rendering surfaces. We know how to manipulate 3D structures and render polygons on a screen using projective geometry. We have had this knowledge since long before computers existed. What has happened in the last 25 years is that computers have increasingly become faster and faster allowing us to render more polygons per second than ever. I am not trying to say that there has not been lots of great research and progress in computer graphics over the years but the evolution of graphics hardware has been a major factor to the development of the real-time photorealistic scenes in computer games today.

When it comes to artificial intelligence and robotics, unfortunately we still don’t have the mathematics that we can build on. Computers have become very powerful over the years but we are still only capable of solving the smallest of AI problems. In robotics, other than faster computers, the rest of the hardware has not developed accordingly. Take for example power sources. Robots today still rely on standard type battery packs that only permit for short operational times usually no more than 1 hour. Additionally, most robots rely on electric motors for locomotion and we are not that close to developing anything as good as human muscles. Finally, there are some artificial intelligence researchers who believe that we have had for years enough computational power to build artificial intelligence agents but we lack the models to do it. Having worked on robotics and AI for almost 10 years, I can tell that having faster computers every year has done little to improve our ability to do such things as teach a robot the ability to navigate a dynamic environment.

In other words, I think that Marshall is wrong and there is absolutely no way that you can infer that robots will evolve over the next 25 years as quickly as games based on the evolution of the latter.

For what it’s worth, here is the video:

Robot archaeologist to explore the pyramid of Cheops at Giza

Scientists will try a second time to send a robot archaeologist down a narrow shaft in the pyramid of Cheops in hopes of revealing its deepest secrets. Four years ago, a similar venture utilizing a specially designed robot supplied by the U.S. iRobot failed to complete its mission after getting blocked by an unexpected obstacle which is believed to be a door or wall restricting access to the inner chamber. That same robot however managed to drill a small hole on the wall and take a pick through to see what is behind. Unfortunately, the scientists found out that there was a small chamber followed by another wall or door. The new and upgraded robot will try to circumvent these obstacles and go through in to the deeper chamber where archaeologists hope to find a treasure.

The teams from Egypt and Singapore and a joint group from Britain and Hong Kong hope to complete the new mission in February 2007 but it is not yet known if the event will be broadcast live just like in 2002. What is hidden deep inside the pyramid is not known with certainty but the teams hope to find Cheops own tomb or maybe some valuable papers and treasures from nearly 2500 B.C.

Best of luck to this robotic Indiana Jones!