Aracna Project Motivation:
Aracna is a new, quadruped robot platform which requires non-intuitive motor commands in order to locomote and thus provides an interesting challenge for gait learning algorithms, such as those frequently developed in the Evolutionary Computation and Artificial Life communities. Aracna is an open-source hardware project composed of off-the-shelf and 3D-printed parts, enabling other research teams to modify its design according to their scientific needs.
You can learn more about the details of this project on the Cornell Creative Machines Lab Website.
What is my Role in this Research?
The goal of developing a robotic platform for evolutionary algorithm development has been pursued for years in the Cornell Creative Machines Lab, where Aracna is under development. Previous to Aracna, “Emergent Self Models” research was pursued via a similar robotic platform. With Aracna, we’re aiming to make that research more accessible to researchers via an open platform. I have been responsible for working on the electronics and writing the embedded firmware. I’ve also developed a wireless serial communication protocol, which is still under development and is fully documented on the github wiki for this project.
See Aracna Move:
This project is still under heavy development, so there will certainly be more videos coming in the future. In the meanwhile, enjoy this video of Aracna in action!.
Aracna Designs, Source Code, and Documentation
Aracna is comprised of entirely open source hardware and software. Current Aracna development is taking place in the GitHub repo linked below. Legacy software can still be found here, and mechanical designs can still be found here. This project is licensed under the GNU General Public (Open-Source) License.
Publications & Presentations:
- Sara Lohmann, Jason Yosinski, Eric Gold, Jeff Clune, Jeremy Blum, and Hod Lipson. Aracna: An open-source quadruped platform for evolutionary robotics. In Proceedings of the 13th International Conference on the Synthesis and Simulation of Living Systems, 2012.
- 2/1/2013 – Featured in Fast Company: “With Evolved Brains, Robots Creep Closer To Animal-Like Learning“
- 2/7/2012 – Featured by Kurzweil: “With evolved brains, robots creep closer to animal-like learning“