Imbalanced expert choices and novel molecular fuzzy decision support systems for energy-efficient autonomous platform investment decisions

• Energy-efficient autonomous platforms are evaluated. • Expert evaluation matrices are balanced. • Selected indicators are prioritized. • Investment strategies are ranked. • Optimization with artificial intelligence-based algorithm is critical. There is no consensus on which critical performance indicators are needed to improve the performance of energy-efficient autonomous platforms. Hence, a priority analysis is needed so that platforms can achieve their efficiency goals. The purpose of this study is to make evaluation for investment decisions of energy-efficient autonomous platforms with a novel model. Firstly, the expert evaluation matrices are balanced via q-learning algorithm. Secondly, selected indicators are prioritized with molecular fuzzy cognitive maps. Finally, investment strategies are ranked by molecular fuzzy multi-objective particle swarm optimization. The biggest contribution is the determination of priority policies for the development of energy efficient autonomous platforms by developing a new and comprehensive model. The development of a new type of fuzzy number in the form of a molecular fuzzy set in the decision-making model is a superiority of the proposed model. As a result, uncertainties in the analysis process can be managed more effectively. It is concluded that optimization with artificial intelligence-based algorithm and statement costs are the most essential performance indicators. Logistics and delivery systems with autonomous electrical vehicles and autonomous climate solutions for smart buildings are also found as the most important investment alternatives of energy-efficient autonomous platforms.