Learning Observation Models with Incremental Non-Differentiable Graph Optimizers in the Loop for Robotics State Estimation

TL;DR

This paper introduces a gradient-based learning approach for observation models in robot state estimation, significantly improving convergence speed and accuracy over existing methods by effectively tuning models in the presence of non-differentiable optimizers.

Contribution

It presents a novel gradient-based learning method tailored for incremental non-differentiable optimizers in robotics, enhancing model tuning and state estimation accuracy.

Findings

Faster convergence to accurate observation models

Improved tracking accuracy on unseen trajectories

Outperforms existing state-of-the-art methods

Abstract

We consider the problem of learning observation models for robot state estimation with incremental non-differentiable optimizers in the loop. Convergence to the correct belief over the robot state is heavily dependent on a proper tuning of observation models which serve as input to the optimizer. We propose a gradient-based learning method which converges much quicker to model estimates that lead to solutions of much better quality compared to an existing state-of-the-art method as measured by the tracking accuracy over unseen robot test trajectories.