RoboGen™ is an open source platform for the co-evolution of robot bodies and brains. It has been designed with a primary focus on evolving robots that can be easily manufactured via 3D-printing and the use of a small set of low-cost, off-the-shelf electronic components. It features an evolution engine, and a physics simulation engine. Additionally it includes utilities for generating design files of body components to be used with a 3D-printer, and for compiling neural-network controllers to run on an Arduino microcontroller board.
Automatic generation of realistic benchmarks and performance profiling of genetic network inference methods. GeneNetWeaver (GNW) was used to generate the international DREAM3 and DREAM4 In Silico Challenges, as well as the DREAM5 Network Inference Challenge. 2008-2011.
Software related to publications
OFVD – Calibrates the viewing direction of optic-flow sensors in the following paper:
A. Briod, J.-C. Zufferey and D. Floreano. Automatically calibrating the viewing direction of optic-flow sensors. Robotics and Automation (ICRA), 2012 IEEE International Conference on, St-Paul, Minnesota, USA, 2012.
CoME – Center of Mass Encoding for the paper:
Mattiussi, C., Dürr, P. and Floreano, D. (2007) Center of Mass Encoding: A self-adaptive representation with adjustable redundancy for real-valued parameters. Proceedings of the Genetic and Evolutional Computation Conference, GECCO2007, University College, London, pp. 1304–1311.
Blimp Model – Code related to the following paper:
Measures of Diversity and Distances – Demo code for the paper:
Mattiussi, C., Waibel, M. and Floreano, D. (2004) Measures of Diversity for Populations and Distances Between Individuals with Highly Reorganizable Genomes. Evolutionary Computation, 12(4) pp. 495–515.