Search-and-rescue (SaR) in unknown environments requires precise, optimal, and fast decisions. Robots are promising candidates for autonomously performing SaR tasks in unknown environments. While humans use their heuristics to effectively deal with uncertainties, optimisation of multiple objectives in the presence of physical and control constraints is a mathematical challenge that requires machine computations. Thus having both human-inspired and mathematical control capabilities is desired for SaR robots. Moreover, coordinating the decisions of robots with little computation cost in large-scale SaR missions is an open challenge. Finally, in real-life data perceived by SaR robots may be prone to uncertainties. We introduce a hierarchical multi-agent control architecture that exploits non-homogeneous and imperfect perception capabilities of SaR robots, as well as the computational efficiency and robustness to failure of decentralised control methods and global performance improvement of centralised control methods. The integrated structure of the proposed control framework allows to combine human-inspired and mathematical decision making methods in a coordinated and computationally efficient way. The results of various computer-based simulations show that while the area coverage of the proposed approach is comparable to existing heuristic methods that are particularly developed for coverage-oriented SaR, the efficiency of the introduced approach in locating the trapped victims is significantly higher. Furthermore, with comparable computation times, the proposed control approach successfully avoids potential conflicts that exist in non-cooperative methods. These results confirm that the proposed multi-agent control system is capable of combining coverage-oriented and target-oriented SaR in a balanced and coordinated way.