We consider a cooperative filtering problem for a group of linear stochastic systems when both absolute linear measurements and relative nonlinear measurements are available. By extending the state of each system with the quadratic part we are able to derive a cooperative filter in the space of the quadratic recursively computable functions of the measurements. The exact value of the variance of the estimation error for each system can be explicitly computed.
2018, 2018 IEEE Conference on Decision and Control (CDC), Pages 7182-7187
Cooperative Filtering with Absolute and Relative Measurements (04b Atto di convegno in volume)
Battilotti S., Cacace F., D'Angelo M., Germani A.
Gruppo di ricerca: Nonlinear Systems and Control