Concertina Gait Learning for Snake Robot using Artificial Neural Network

In this project we have tested evolutionary process on concertina motion of snake robot. Concertina motion is a type of gait in snake in which it draws its body into sine curve then motion begins by extending its head and forward parts of the body by using frictional forces. This type of gait enable snake to move in narrow spaces. Here we have designed our snake robot in Bullet-Physics environment while Hill-Climber algorithm which is a genetic algorithm has been used to optimize the Artificial Neural Network for to give our robot the evolving capability. A multi-objective Fitness Function is designed in bullet-physics engine which reinforces learning of sinusoidal curve in snake and also reinforces forward motion in it. This multi-objective function seems to be promising as compare to single-objective as it considers the shape of the robot and takes into account the distance as well. Here in our experiment the locomotion controller quickly evolved and the desired behaviors have been obtained. Concertina motion with the proposed evolving capabilities make it a good solution for designing basic motion pattern for snake robots.