Karlsruhe Institute of Technology
A new method for globally optimal estimation in decentralized sensor-networks is applied to the decentralized control problem. The resulting approach is proven to be optimal when the nodes have access to all information in the network. More precisely, the authors utilize an algorithm for optimal distributed estimation in order to obtain local estimates whose combination yields the globally optimal estimate. When the interconnectivity is high, the local estimates are almost optimal, which motivates the application of the principle of separation. Thus, they optimize the controller and finally obtain a flexible algorithm, whose quality is evaluated in different scenarios.