A bipolar fuzzy integrated decision making model for underwater robot selection

Robots play a crucial role in various sectors, including medicine, aeronautics, the military, and the marine industry. The rapid advancement of robotic technologies has made the selection process for specific operations increasingly complex. Existing multi-attribute decision-making models often fail to capture interdependencies among attributes or examine contradictory expert opinions. To address these challenges, this study proposes an integrated decision-making system that combines the digraph-matrix approach with multi-attribute ideal-real comparative analysis to prioritize underwater robots. The system employs interrelations and bipolar fuzzy positive determinants to assess pairwise attribute importance and overall performance, respectively. Furthermore, a novel ranking function is defined to facilitate the defuzzification process. An application on underwater robot selection for offshore oil and gas operations demonstrates the model's effectiveness. The results reveal that the proposed system provides consistent rankings under varying conditions and outperforms traditional methods in capturing counter-judgments and inter-criteria dependencies. By incorporating bipolar fuzzy logic, the model enables the selection of energy-efficient and cost-effective robots, thereby minimizing environmental impact and reducing carbon footprints in deep-sea operations. Finally, comparative analysis confirms the system's superiority.