Efficient and precise sensor fusion for non-linear systems with out-of-sequence measurements by example of mobile robotics

Abstract

For most applications in mobile robotics, precise state estimation is essential. Typically, the state estimation is based on the fusion of data from different sensors. In practice, these sensors differ in their characteristics and measurements are available to the sensor fusion algorithm only with delay. Based on a brief survey of sensor fusion approaches that consider delayed and out-of-sequence availability of measurements, suitable approaches for applications in mobile robotics are identified. In a consumer robot use-case, experiments show that the estimation is biased if delayed availability of measurements is not considered appropriately. However, if delays are considered in the fusion process, the estimation bias is reduced to almost zero and in consequence, the estimation performance is distinctly improved. Two computational favorable approximative methods are described and provide almost the same accuracy as - theoretically optimal - brute-force filter recalculation at much lower and well-distributed computational costs.