Life in the Robotics Lab

They kept repeating: it is not about research, this is about product creation!

One of the things that shocked me when I started to work for PAL Robotics some years ago was the required change in mentality. A change was necessary from a research based mind to a company based one. I almost remember myself thinking: you are in the army now!.

Yes! It worked once! Let's write a paper!Let's put it clear: a robot product must work correctly all the time. It is not enough to make it work for a promotional advertising, for a short demo, or to make a video for a conference paper on a very specific situation and condition. It must work under all the circumstances it is supposed to be when in its operating environment. Under all light conditions, under all noise conditions, under all crowds size. And let's face it, this is a tough job. Especially because we are talking about real hardware, no computer simulations.

Because of that, the mentality inherited from the time spent at University doing research is not valid any more. At least in its purest form...

Some time ago, I heard a well reputed SLAM researcher say that SLAM was a solved problem. So, he was proposing, why don't we move on to studying another thing?.

Well, I wouldn't go that far. One can say at most that  in theory the problem is solved. It is like those problems on physics about using spherical cows.

I would say from my experience that robust SLAM is far from being solved. At least when using real robots with no adapted environment. Spherical cows do not exist in real life.

Experimenting with real robot REEM-BAnd that is what we are talking about here: real robots with real hardware, with real interferences between sensors, real battery problems, real CPU constraints, and more important than anything, real unpredictable environments. And under those conditions, current SLAM techniques do not work. What for a research mind seems a solved problem, for a product-generation mind seems almost useless.

So here we are. We need to solve a practical problem, which has a theoretical solution which doesn't work at practice. And here is where, paradoxically, our research mind comes to the rescue. A research mind is required to find a new solution to the problem, but having as a target the generation of a real life solution, rather than a paper publication one.

This means that one can apply the research methodology and add the necessary twist to adapt an existing research solution, modify it, or completely create a new one for that problem. Using this approach you can, for instance, construct a complete SLAM system which works on a humanoid robot.

So after all, the complete change of mind was not so necessary but instead, a change of focus.

The Zen master said, you must learn the path, follow the path and then forget the path. And that is exactly what happened to our mind when we moved from research to company work. However, in the process nothing remained the same. The path remains in our essence, hence, it can come to the rescue when needed, applying it to the place that is most required.

Just remember to enjoy the path.

Tags: robots, robust

The design of our robot REEM: a well studied topic

Hi, I am Jan, and I am the Business Developer here in PAL Robotics. A very challenging job, in a company loaded with very intelligent and ambitious engineers, and in a world where we are at the very early stage of introducing robotics in society.   I just want to share a couple of words with you on one of the main issues of our robots: its design.

My task here is to sell these cute robots we make. But…how do you sell a robot? Many references from the market I did not get – there are for the moment not too much robots around, which, in a certain way, is good for us!  So we did a careful study to check what´s been done, and what failed and why and so on…and actually quite soon you find out that all these smart engineers worldwide make wonderful pieces of technology, but quite often they lack a nice design.

Why do so many people buy iPods and iPhones (see www.apple.com)? Because it is such a sleaky, slim and sexy tool! Yes, definitely in the case of Apple´s bestseller, the design is not the only, but a very important sales argument. And what counts for Apple, counts for a lot of brands and products.

So, why do robots not sell like iPods? ;) Well, there are of course hundreds of reasons (lack of offer, price, security, applications,…) , but one fact is surely people do not feel comfortable yet with robots, a.o. because the physical outlooks of the robots are not very attractive, and because they do not invite people to interact with the robot.

We spend a lot of time and effort in looking for a very aesthetical outlook for REEM, our latest prototype. Just to give you an idea; we organized public demonstrations (although with another model) to check out the reactions of the public (you can see some videos of these on our website, we paid attention to the movements of the robot and how that influences the interaction with people and we gave it a soft voice which is nice to listen to.

The result you will be able to see on both our blog and website – I hope you like it!

Please note that the design of REEM has been developed in-house, contrary to the design of  REEM-C, the new biped robot, for which we have a contest running on our blog.

Tags: Apple, humanoid, PAL, PAL Robotics, Podcast, REEM, REEM-C, robot, service robot

At the beginning of this year we offered students from several universities the opportunity to do their internship at our lab, and as a result we now have seven interns at our premises making a great contribution to our research and development activities! Time to introduce to you our Class of 2010!

Pablo Garcia is from Albacete, a small city close to Madrid. He decided to come to Barcelona to do the Masters Automation and Robotics at the UPC (Universidad Politecnica de Calatuña). In the morning he works at our lab and in the afternoon he works on his final master’s project: "Automatic Calibration of the Odometry and Laser Sensor Parameters in Mobile Robots". ‘At PAL Robotics there is an exceptional atmosphere. Everybody works really hard but people are always in a good mood! I think this is one of the most important things about working in a group!'

Victor López is from Barcelona, he studied at UPC in the Barcelona School of Informatics (FIB). He’s working on a Supervisor Agent for a Humanoid Robot framework and has been working at PAL Robotics since 5 months. During his time at the company he has learned a lot about robotics, software design and specially C++ programming. ‘This internship has been a great opportunity because I believe I've been very lucky to work with and learn from such brilliant people that work here.’

Jordan Palacios is from Argentina and has been living in Spain for six and a half years now. He recently started working at the lab and still doesn't have a clear project in mind. Though he would like to start something very soon! ‘So far PAL seems great, the environment is relaxed and cheerful, combined with the perfect amount of hard work and dedication.’

Michael Delgado is a Barcelona native and studies at FIB (Facultat d'Informàtica de Barcelona). At the moment he’s finishing the last subjects of this year.  His work at PAL Robotics is focused on programming interfaces. Michael enjoys working in a multilingual team. ‘Working at PAL Robotics is awesome! I’m learning a lot about programming and at the same time I’m improving my language skills.’

From left to right: Pablo, Victor, Jordan and Michael

Tags: intern, internship

Today our colleague José told us that in a few months he will become a father. You should also know that our secretary, Alicia, is at the end of her 8^th months of pregnancy (she is already at home and we are awaiting news from here pretty soon. Sergi’s wife is pregnant, Joan will have his second child after the summer and I will become a father in November as well!

If you spend some time in PAL Robotics, you will find that we look like the subjects of an experiment about fertility and reproduction. Every 2-3 months we have a party for this reason: some of us go for the first child, while others are already gunning for the second.

Apparently, there is an undercover gambling going on about who is going to be next (I have been a candidate for more than one year, but there always was someone else getting there first…).

Tags: lab