Evolving Controllers for Physical Multilegged Robots
Active from 2010 - 2011
Evolving controllers for multilegged robots in simulation is convenient and flexible, making it possible to prototype ideas rapidly. However, transferring the resulting controllers to physical robots is challenging because it is difficult to simulate real-world complexities with sufficient accuracy. This project bridges this gap by utilizing the Evolution of Network Symmetry and mOdularity (ENSO) approach to evolve modular neural network controllers that are robust to discrepancies between simulation and reality. This approach was evaluated by building a physical quadruped robot and by evolving controllers for it in simulation. An approximate model of the robot and its environment was built in a physical simulation and uncertainties in the real world were modeled as noise. The resulting controllers produced well-synchronized trot gaits when they were transferred to the physical robot, even on different walking surfaces. In contrast to a hand-designed PID controller, the evolved controllers also generalized well to changes in experimental conditions such as loss of voltage and were more robust against faults such as loss of a leg, making them strong candidates for real-world applications.

Videos of evolved walking behaviors
Vinod Valsalam Ph.D. Alumni vkv [at] alumni utexas net
Risto Miikkulainen Faculty risto [at] cs utexas edu
Constructing Controllers for Physical Multilegged Robots using the ENSO Neuroevolution Approach Vinod K. Valsalam, Jonathan Hiller, Robert MacCurdy, Hod Lipson and Risto Miikkulainen Evolutionary Intelligence, 5(1):1--12, 2012. 2012

Evolving Symmetry for Modular System Design Vinod K. Valsalam and Risto Miikkulainen IEEE Transactions on Evolutionary Computation, 15(3):368--386, 2011. 2011

Utilizing Symmetry in Evolutionary Design Vinod Valsalam PhD Thesis, Department of Computer Sciences, The University of Texas at Austin, Austin, TX, 2010. Te... 2010

ENSO This package contains software implementing the ENSO approach for evolving symmetric modular neural networks. It also in... 2010