ConFusion: Sensor Fusion for Complex Robotic Systems using Nonlinear Optimization
This work addresses sensor fusion challenges for robotic systems, offering a flexible and scalable solution, though it appears incremental as it builds on existing moving horizon estimator concepts.
The authors tackled the problem of online sensor fusion for robotics by introducing ConFusion, a modular framework using nonlinear optimization, which demonstrated improved performance over an iterated extended Kalman filter in visual-inertial tracking and versatility in whole-body sensor fusion on a mobile manipulator.
We present ConFusion, an open-source package for online sensor fusion for robotic applications. ConFusion is a modular framework for fusing measurements from many heterogeneous sensors within a moving horizon estimator. ConFusion offers greater flexibility in sensor fusion problem design than filtering-based systems and the ability to scale the online estimate quality with the available computing power. We demonstrate its performance in comparison to an iterated extended Kalman filter in visual-inertial tracking, and show its versatility through whole-body sensor fusion on a mobile manipulator.