Path planning of humanoid robots on complex terrains using an efficient regression-based chaotic Harris Hawks optimization approach

Abstract

PurposeOptimal navigation and trajectory planning are in high demand because of the rise in automated systems. This study aims to focus on implementing an intelligent regression-based chaotic Harris Hawk optimization (LR-CHHO) to achieve a globally optimal path free from collisions.Design/methodology/approachThis study removes the drawbacks of the existing HHO model in terms of its exploration and exploitation behaviors. After the threat is encountered, the improved controller is activated. The LR tool, here, avoids the issue related to the sensitivity of the model. The virtual Hawks, as per the HHO technique, are generated and trained to enhance the diversity in Hawks population. The final controller then calculates the optimal turn angle for the humanoid to avoid threats before reaching the goal.FindingsModel showed an overall improvement greater than 4% in the path and 9% in time compared with standard models in Terrains 1 and 2. Regarding energy efficiency, a significant improvement of more than 20% in the hip, 14% in the knee and 30% in the ankle was observed on both even and uneven terrains.Originality/valueThe originality of this study focuses on improving the diversity in the HHO population by introducing the LR-based model to help the humanoids find an optimal path to the goal. Although the basic model lacked an optimal solution because of sensitivity, less diversity, etc., the proposed model helped resolve the issue and achieve an optimal turning angle for the humanoids to trace the optimal path.