Legged robot gait locus generation based on genetic algorithms

Achieving an effective gait locus for legged robots is a challenging task. It is often done manually in a laborious way due to the lack of research in automatic gait locus planning. Bearing this problem in mind, this article presents a gait locus planning method using inverse kinematics while incorporating genetic algorithms. Using quadruped robots as a platform for evaluation, this method is shown to generate a good gait locus for legged robots.

[1]  Thomas G. Dietterich What is machine learning? , 2020, Archives of Disease in Childhood.

[2]  Peter Stone,et al.  Machine Learning for Fast Quadrupedal Locomotion , 2004, AAAI.

[3]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .

[4]  K. De Jong Adaptive System Design: A Genetic Approach , 1980, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  Peter Stone,et al.  A Model-Based Approach to Robot Joint Control , 2005, RoboCup.

[6]  Francis L. Merat,et al.  Introduction to robotics: Mechanics and control , 1987, IEEE J. Robotics Autom..

[7]  Hiroaki Kitano,et al.  RoboCup: A Challenge Problem for AI , 1997, AI Mag..

[8]  Jan Hoffmann,et al.  Reliable and Precise Gait Modeling for a Quadruped Robot , 2005, RoboCup.

[9]  Kenneth de Jong,et al.  Adaptive System Design: A Genetic Approach , 1980, IEEE Trans. Syst. Man Cybern..

[10]  Joe Suzuki,et al.  A Markov chain analysis on simple genetic algorithms , 1995, IEEE Trans. Syst. Man Cybern..

[11]  Hiroaki Kitano,et al.  A Challenge Problem for AI , 1997 .