Active collaboration in relative observation for Multi-agent visual SLAM based on Deep Q Network

This paper proposes a unique active relative localization mechanism for multi-agent Simultaneous Localization and Mapping(SLAM),in which a agent to be observed are considered as a task, which is performed by others assisting that agent by relative observation. A task allocation algorithm based on deep reinforcement learning are proposed for this mechanism. Each agent can choose whether to localize other agents or to continue independent SLAM on it own initiative. By this way, the process of each agent SLAM will be interacted by the collaboration. Firstly, based on the characteristics of ORBSLAM, a unique observation function which models the whole MAS is obtained. Secondly, a novel type of Deep Q network(DQN) called MAS-DQN is deployed to learn correspondence between Q Value and state-action pair,abstract representation of agents in MAS are learned in the process of collaboration among agents. Finally, each agent must act with a certain degree of freedom according to MAS-DQN. The simulation results of comparative experiments prove that this mechanism improves the efficiency of cooperation in the process of multi-agent SLAM.