Humanoid Robot Path Planning Using Memory-Based Gravity Search Algorithm and Enhanced Differential Evolution Approach in a Complex Environment

The present work focuses on an optimal path planning of single and multiple humanoid robots in a rugged terrain using a hybrid-based improved gravitational search algorithm (IGSA) tuned differentially perturbed velocity (DV) approach. The primary gravity search algorithm (GSA) suffers from the disadvantage of a lower convergence rate and getting trapped in local optimum conditions. The drawback is removed by using the hybrid IGSA-DV path planning approach, which improves the memory and velocity updating scheme. The algorithm is designed to minimize the overall path length of the humanoid, from source to goal, in the minimal time possible. The humanoids, during their locomotion, coordinate with each other to avoid collisions in their journey. The robots, primarily, make the decision based on the position of the various obstacles within the search space. The path smoothness is also considered to ensure stability and path optimization during the locomotion. The work further focussed on the energy efficiency of the different joints of the humanoid while walking on an even and uneven surface. The work is performed in real-world and simulation environments, and the results are then compared with the different existing, individual and hybrid techniques. The comparison of the above approach revealed that the IGSA-DV algorithm showed a better optimal outcome in terms of path length and time taken. Moreover, the deviation in simulation and experimental results was within the acceptable limits (less than 6%). Petri-Net approach was introduced along with the proposed technique to avoid confusion among the robots during path navigation.