Study of Joint Symmetry in Gait Evolution for Quadrupedal Robots Using a Neural Network

Abstract

Bio-inspired legged robots have the potential to traverse uneven terrains in a very efficient way. The effectiveness of the robot gait depends on the joint symmetry of the robot; variations in joint symmetries can result in different types of gaits suitable for different scenarios. In the literature, symmetric and asymmetric gaits have been synthesized for legged robots; however, no relation between the gait effectiveness and joint symmetry has been studied. In this research work, the effect of joint symmetry on the robot gait is studied. To test the suggested algorithm, spider-like robot morphology was created in a simulator. The simulation environment was set to a flat surface where the robots could be tested. The simulations were performed on the PyroSim software platform, a physics engine built on top of the Open Dynamics Engine. The quadrupedal robot was created with eight joints, and it is controlled using an artificial neural network. The artificial neural network was optimized using a genetic algorithm. Different robot symmetries were tested, i.e., diagonal joint symmetry, diagonal joint reverse symmetry, adjacent joint symmetry, adjacent joint reverse symmetry and random joint symmetry or joint asymmetry. The robot controllers for each joint symmetry were evolved for a set number of generations and the robot controllers were evaluated using a fitness function that we designed. Our results showed that symmetry in joint movement could help in generating optimal gaits for our test terrain, and joint symmetry produced gaits that were already present in nature. Moreover, our results also showed that certain joint symmetries tended to perform better than others in terms of stability, speed, and distance traveled.