A partially decentralized EKF scheme for cooperative localization over unreliable communication links

This paper reports a partially decentralized implementation of an Extended Kalman filter for the cooperative localization of a team of mobile robots with limited onboard resources. Unlike a fully centralized scheme that requires, at each timestep, information from the entire team to be gathered together and be processed by a single device, our algorithm only requires that the robots communicate with a central command unit at the time of a measurement update. Every robot only needs to propagate and update its own state estimate, while the central command unit maintains track of cross-covariances. Therefore, the computational and storage cost per robot in terms of the size of the team is of order O(1). Moreover, when the system model is linear the algorithm is robust to occasional in-network communication link failures while the updated estimates of the robots receiving the update message are of minimum variance at that given timestep. For problems with nonlinear robot models, our algorithm under message drop-out provides a suboptimal solutions because of the linearization approximation similar to the Extended Kalman filter model. We demonstrate the performance of the algorithm in simulation.