Quantcast

Humanoid robots and technology in general have always fascinated me. This caused my parents lots of trouble during my childhood. I would secretly disassemble pretty much all the electrical devices in our household in hope to understand the underlying principles that made them work.

As I grew up, this curiosity broadened and I started asking questions about the fundamental principles of the universe, the nature of reality and our consciousness. I finished an engineering school in my home country Slovakia and soon after moved to the United Kingdom where I studied computing and astronomy.

Nowadays, I do a PhD at The University of Plymouth for the iTalk project (Integration of Action and Language in Humanoid Robots). The iTalk project (www.italkproject.org) proposal beat the competition from 31 other applications and won a £4.7 million grant from The European Commission’s Seventh Framework Programme. This highly ambitious project, coordinated by my supervisor Professor Angelo Cangelosi, aims at developing biologically-inspired artificial systems that can progressively develop their cognitive capabilities through the interaction with their environments.

Based on the insights from neuroscience, developmental psychology, robotics, linguistics and others we argue that cognitive skills (e.g. memory, reasoning, symbolic thinking, visual and auditory processing, etc.) have their foundations in the morphology and material properties of our bodies. The iTalk project emphasizes the role of embodiment by using one of the most complex humanoid robots in the world. This intricate humanoid robotic platform called iCub is approximately 105cm high, weights around 20.3kg and was designed by the RobotCub Consortium (www.robotcub.com).

I originally heard about the CUDA framework from a Russian friend who was planning to use it to accelerate the Mars Rover Simulator that I previously developed during our collaboration with ESA (European Space Agency). I could not spend any more time on the ESA research, as I had to resume my PhD and proceed with the research. However, one day I found an article about a neural network implementation using CUDA and I was impressed by the performance increases that were achieved. A day later, I showed the article to my colleague Anthony Morse and after many discussions we agreed that GPU processing is exactly what we needed in our laboratory as most of the systems we use can easily be parallelised.

We looked into OpenCL as an alternative but CUDA framework provided much more support and the API was really good. Therefore we decided to go with CUDA, ordered six servers with several Tesla C1060 and GeForce GTX470 cards and created a Linux based supercomputing cluster for an affordable price that is capable of performing over 12TFLOPS (trillion operations per second). In order to start utilising this power we began the development of CUDA-enabled software named Aquila that is tailored for the iCub humanoid robot and the execution of several different bio-inspired systems.

For my PhD research, I use Aquila to develop complex artificial neural networks, inspired by those found in the brain, and use them for the real-time control of the iCub robot. These artificial neural networks often consist of thousands of neurons that are connected to many other neurons as well as to several modalities (somatosensory, vision, language, etc.) of the iCub robot through millions of synaptic connections. The multidimensional input from various senses is abstracted into internal representations meaningful to the system. This is achieved through the use of so-called self-organising maps, which closely resemble the topologically organised cortices found in the brain. Often reaching sizes of several thousands neurons, these maps are abstracting the original visual data obtained through the process of applying special filters to millions of pixels. Apart from this visual processing, the system needs to work with linguistic and somatosensory inputs while performing millions of calculations needed to activate the neural network at every 50-100ms.

CUDA framework accelerated the online neural network control several hundred times on average, and the algorithms responsible for iCub’s training showed around 50x speed increase. I have developed both CPU and GPU versions and although I haven’t completed extensive optimisations, the nice thing about CUDA is that simply by naïve parallelisation of the CPU code one can achieve massive speedups using GPU devices.

As quantum computing is still in its infancy, to me it seems that massively parallel GPU processing is the way to move forward since CPU architectures are simply not suited for parallel tasks, consume too much energy and do not scale well.

  • Euphobia

    Amazing. I love seeing things that can help advance AI, and CUDA seems to be definitely one of them.

    I’m about to begin studying AI at University next semester as I find it the most fascinating aspect in computing.d

  • http://www.facebook.com saurabh mazumder

    i am saurabh mazumder a student of electronics and telecommunication from india sir i really appretiate your work…welll i have also made some research on the advancements in the technology of nvdia gpu’s powered with cuda and physx well physx is really a powerful software with which we really can do wonders well its my 2 years research and workflow i finally came with ma mod where now all nvdia users can now seamlessly play all games in all settings high (all eye candies on) no matter if it is p4 3 ghz or the next gen pocessors now physx can lift all the processing our pc needs though out the resources in the pc and trans from any lame pc into super computing device..well its new evolutin of modding where no harware modifiction is required no overclocking a simple cod can make wonders ever seen or ever witnessed ..i am disrtibuting a demo copy of my software so that u can experience the wonder …if interested can contact me at saurabh.maxpayne@gmail.com well its only the begining of new mod named GOD which can make wonders it directly commands the hardware to perform the work seamlessly whic was earlier controlled by hardware………lastly all i neeed is your support and a platform to show my researchwork

  • http://www.martinpeniak.com Martin Peniak

    Thank you for your comments, I very much appreciate it.

    @Euphobia – I don’t think you will regret if you start studying AI. It is an incredibly diverse field covering anything between psychology, philosophy, biology, neuroscience, robotics and computing, that’s why I love it so much. The current level of AI is in my opinion pretty much comparable to that of a retarded cockroach so there is lots of areas you can investigate and make contributions to. Good luck!

    @Saurabh – That does sound like an interesting mod, I like the name too :D Please send me a copy and let me know if you are interested in having your software featured on my site.

  • http://www.facebook.com saurabh mazumder

    @ martin ya sure i am really interested to make my mod to be featured in ur site…..my i have ur mailid so that i can mail u the link

  • http://www.martinpeniak.com Martin Peniak

    Please contact me through my website: http://www.martinpeniak.com

  • http://www.facebook.com saurabh mazumder

    @martin i have sent u a facebook request plz heck it as i am also in facebook tooo

  • http://www.facebook.com saurabh mazumder

    @ martin i havesend u the mail as per ur given web site mail process if then also u didnt recieve the mai ..plz let me know
    regards
    saurabh mazumder