This paper proposes a structural simulation environment for cognitive systems that effectively models both bottom-up emergent needs derived from sensory data and top-down task specifications for actuator control. The proposed simulation structure is both scalable and explainable; needs emerge concurrently. The tasks triggered to fulfil these needs follow a hierarchical top-down approach. Experimental results demonstrate that the simulation environment accurately models the hunger and play needs of a fully autonomous pet robot, all within the overall goal of the robot’s survival.