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

2023/09/05 by Qadri, Mohamad, Kaess, Michael
#FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2309.02525

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.

Related

• LEO: Learning Energy-based Models in Factor Graph Optimization
• Learning Covariances for Estimation with Constrained Bilevel Optimization
• LEARNEST: LEARNing Enhanced Model-based State ESTimation for Robots using Knowledge-based Neural Ordinary Differential Equations
• STEADY: Simultaneous State Estimation and Dynamics Learning from Indirect Observations
• Differentiable Factor Graph Optimization for Learning Smoothers