This video demonstrates how Aquila trains and runs multiple time-scales recurrent neural networks used to control humanoid robot iCub (http://www.robotcub.org/) in real time.
The results shown in this video are from the initial tests only and are meant to demonstrate the potential of neural system (based on Jun Tani's architecure) as well as the massive speed-ups achieved by running the network on parallel CUDA devices such as the latest NVidia Fermi architecture.
I am currently working on extending the neural system with additional modalities dealing with vision, extra proprioception as well as language so keep eyes on my site for new results. I reckon it is going to get more interesting as we proceed farther with our investigation into how actions and language co-develop in the brain.
Legacy article – Robotics, GPU and research
Aquila running mutiple time-scales recurrent neural network on iCub humanoid robot
- Original publication date
- 2 November 2010
- Original section
- Robotics, GPU and research
- Original slug / legacy ID
- aquila-running-mutiple-time-scales-recurrent-neural-network-on-icub-humanoid-robot / 182
- Restored on current site
- martinpeniak.com/archive/writing/aquila-running-mutiple-time-scales-recurrent-neural-network-on-icub-humanoid-robot/
- Editing scope
- Period voice retained; spelling and formatting lightly cleaned.
Originally published 2 November 2010 on the earlier martinpeniak.com site.
Preserved from the old research notes as a full article. The article keeps its period voice, with light formatting cleanup.