Toward automatic gait generation for quadruped robots using cartesian genetic programming

Authors:
Kisung Seo;Soohwan Hyun
Affiliations:
Dept. of Electronic Engineering, Seokyeong University, Seoul, Korea;Hyundai Heavy Industries Research Institute, Yongin, Korea
Venue:
EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation
Year:
2013

Citing 6
Cited 1

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Genetic programming II: automatic discovery of reusable programs

Genetic programming II: automatic discovery of reusable programs
Principles in the Evolutionary Design of Digital Circuits—Part I

Genetic Programming and Evolvable Machines
Cartesian Genetic Programming

Proceedings of the European Conference on Genetic Programming
A comparative study between genetic algorithm and genetic programming based gait generation methods for quadruped robots

EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I
Autonomous evolution of dynamic gaits with two quadruped robots

IEEE Transactions on Robotics

GECCO 2013 tutorial: cartesian genetic programming

Proceedings of the 15th annual conference companion on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a new gait generation method for quadruped robots using CGP (Cartesian Genetic Programming) based on refinement of regression polynomials for a joint trajectory. CGP uses as genotype a linear string of integers that are mapped to a directed graph. Therefore, some evolved modules for regression polynomials in CGP can be shared and reused among multiple outputs for joint trajectories. To investigate the effectiveness of the proposed approach, experiments on gaits were executed for a Bioloid quadruped robot in the Webots environment.