Saved in:
Bibliographic Details
Main Authors: Benhamou, Jonas, Bonnabel, Silvère, Chapdelaine, Camille
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.17569
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913257521938432
author Benhamou, Jonas
Bonnabel, Silvère
Chapdelaine, Camille
author_facet Benhamou, Jonas
Bonnabel, Silvère
Chapdelaine, Camille
contents To enhance accuracy of robot state estimation, active sensing (or perception-aware) methods seek trajectories that maximize the information gathered by the sensors. To this aim, one possibility is to seek trajectories that minimize the (estimation error) covariance matrix output by an extended Kalman filter (EKF), w.r.t. its control inputs over a given horizon. However, this is computationally demanding. In this article, we derive novel backpropagation analytical formulas for the derivatives of the covariance matrices of an EKF w.r.t. all its inputs. We then leverage the obtained analytical gradients as an enabling technology to derive perception-aware optimal motion plans. Simulations validate the approach, showcasing improvements in execution time, notably over PyTorch's automatic differentiation. Experimental results on a real vehicle also support the method.
format Preprint
id arxiv_https___arxiv_org_abs_2402_17569
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Backpropagation-Based Analytical Derivatives of EKF Covariance for Active Sensing
Benhamou, Jonas
Bonnabel, Silvère
Chapdelaine, Camille
Robotics
To enhance accuracy of robot state estimation, active sensing (or perception-aware) methods seek trajectories that maximize the information gathered by the sensors. To this aim, one possibility is to seek trajectories that minimize the (estimation error) covariance matrix output by an extended Kalman filter (EKF), w.r.t. its control inputs over a given horizon. However, this is computationally demanding. In this article, we derive novel backpropagation analytical formulas for the derivatives of the covariance matrices of an EKF w.r.t. all its inputs. We then leverage the obtained analytical gradients as an enabling technology to derive perception-aware optimal motion plans. Simulations validate the approach, showcasing improvements in execution time, notably over PyTorch's automatic differentiation. Experimental results on a real vehicle also support the method.
title Backpropagation-Based Analytical Derivatives of EKF Covariance for Active Sensing
topic Robotics
url https://arxiv.org/abs/2402.17569