Adaptive Robust Kernels for Non-Linear Least Squares Problems
This work addresses the need for automated parameter tuning in robust state estimation for robotics, offering an incremental improvement over existing methods.
The paper tackles the problem of manually tuning robust kernels for outlier handling in least squares state estimation by proposing an adaptive kernel family that automatically tunes based on residual distribution, and it shows higher robustness in tests on ICP and bundle adjustment problems in robotics.
State estimation is a key ingredient in most robotic systems. Often, state estimation is performed using some form of least squares minimization. Basically, all error minimization procedures that work on real-world data use robust kernels as the standard way for dealing with outliers in the data. These kernels, however, are often hand-picked, sometimes in different combinations, and their parameters need to be tuned manually for a particular problem. In this paper, we propose the use of a generalized robust kernel family, which is automatically tuned based on the distribution of the residuals and includes the common m-estimators. We tested our adaptive kernel with two popular estimation problems in robotics, namely ICP and bundle adjustment. The experiments presented in this paper suggest that our approach provides higher robustness while avoiding a manual tuning of the kernel parameters.