Lagrange programming neural network for robust passive elliptic positioning

Abstract

This contribution studies passive elliptic positioning (PEP) with unknown transmitter locations, a localization technique having great potential applicability ranging from underwater wireless sensor networks to intelligent transportation systems. Specifically, we aim to address the challenge of employing PEP in complex real-world environments where outliers may exist, by using the concept of robust statistics. To achieve such a goal, we replace the ℓ2 loss in the traditional nonlinear least squares formulation by a differentiable cost function that possesses outlier-resistance. The neurodynamic approach of Lagrange programming neural network is then adopted to solve the resultant nonconvex statistically robustified PEP problem in a computationally efficient manner. Simulations and acoustic positioning experiments demonstrate the performance superiority of our proposal over its competitors.