We propose a multi-robot exploration algorithm that uses adaptive coordination to provide heterogeneous behavior. The key idea is to maximize the efficiency of exploring and mapping an unknown environment when a team is faced with unreliable communication and limited battery life (e.g., with aerial rotorcraft). The proposed algorithm utilizes four states: explore, meet, sacrifice, and relay. The explore state uses a frontier-based exploration algorithm, the meet state returns to the last known location of communication to share data, the sacrifice state sends the robot out to explore without consideration of remaining battery, and the relay state lands the robot until a meeting occurs. This approach allows robots to take on the role of a relay to improve communication between team members. In addition, the robots can “sacrifice” themselves by continuing to explore even when they do not have sufficient battery to return to the base station. We compare the performance of the proposed approach to state-of-the-art frontier-based exploration, and results show gains in explored area. The feasibility of components of the proposed approach is also demonstrated on a team of two custom-built quadcopters exploring an office environment.