Towards Combining Robotic Algorithms and Machine Learning: End-To-End Learnable Histogram Filters

Problem-specific robotic algorithms and generic machine learning approaches to robotics have complementary strengths and weaknesses, trading-off data-efficiency and generality. To find the right balance between these, we propose to use robotics-specific information encoded in robotic algorithms together with the ability to learn task-specific information from data. We demonstrate this approach in a proof of concept: the end-to-end learnable histogram filter. This fully differentiable implementation of a histogram filter encodes the structure of recursive state estimation using prediction and measurement update but allows the specific models to be learned end-to-end, i.e. in such a way that they optimize the performance of the filter, using either supervised or unsupervised learning.