Humanoid path planning on even and uneven terrains using an efficient memory-based gravitational search algorithm and evolutionary learning strategy

Abstract

The increasing demand for automation and material transportation has shown an incline toward optimal path navigation. The present work implements an intelligent Memory-based gravitational search algorithm (MGSA) with an evolutionary learning strategy to achieve a globally optimal collision-free path. The Evolutionary learning strategy helps improve the diversity among the Gravitational masses/agents, hence improving the overall exploration capability of the model. While the other approaches focus more on an evolutionary strategy based on mutation and cross-overs, the present technique implements the evolutionary strategy based on the position of the fit agents to improve the position of the unfit agents in the population. It ensures a fast-converging path planning result with an improved trajectory. Further, adding a memory-based approach helps the model remember the location of the best agent within the population. The controller is tested with multiple Humanoids on even and uneven terrains and showed a minimal improvement of more than 4% in path length with a minimum 5% deviation in the simulation and experimental results. The proposed approach showed a further improvement of more than 6% compared to the different intelligent path-planning approaches in a similar environment.