VICTIM LOCALIZATION USING DARWINIAN IMPERIALIST COMPETITIVE ALGORITHM

摘要

Grid search for the victim in unknown environments using a swarm of robots tend to be not practical. Many research has been done using evolutionary algorithms for victim localization. The search problem is modelled as an optimization problem. The convergence to the optimal solution is one of the key factors in such a problem. Due to the harsh and unpredictable nature of the environment, cooperative navigation and victim identification in these environments are incredibly challenging to achieve. The obstacle avoidance, collision of robots and intra communication between them are still needed to assist the victim localization process in unpredictable situations. In this study, the Robotics Darwinian Imperialist Competitive Algorithm (RDICA) algorithm has been used for victim localization, to avoid a local optima problem, the exploration facility using do-revolution feature has been used. According to multiple experiments that conducted under different scenarios, distinctive results have been revealed. The average of crashed robots significantly reduced. Moreover, a 7.3 and 6.93% achieved improvement over the well-known state of the arts DPSO and RDPSO algorithms respectively while preserving the comparable number of iterations adequate to gain these results.