Design of a hybrid controller using genetic algorithm and neural network for path planning of a humanoid robot

Abstract

Purpose To navigate humanoid robots in complex arenas, a significant level of intelligence is required which needs proper integration of computational intelligence with the robot's controller. This paper describes the use of a combination of genetic algorithm and neural network for navigational control of a humanoid robot in given cluttered environments. Design/methodology/approach The experimental work involved in the current study has been done by a NAO humanoid robot in laboratory conditions and simulation work has been done by the help of V-REP software. Here, a genetic algorithm controller is first used to generate an initial turning angle for the robot and then the genetic algorithm controller is hybridized with a neural network controller to generate the final turning angle. Findings From the simulation and experimental results, satisfactory agreements have been observed in terms of navigational parameters with minimal error limits that justify the proper working of the proposed hybrid controller. Originality/value With a lack of sufficient literature on humanoid navigation, the proposed hybrid controller is supposed to act as a guiding way towards the design and development of more robust controllers in the near future.