Optimal State Estimation for DNN Visual Servoing Systems with Detection Loss

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

1 Downloads (Pure)

Abstract

The introduction of deep learning techniques, such
as object detection in visual servoing systems, has produced
more sophisticated robotic systems capable of working in
unknown environments. However, the interaction between the
object detection network and the controller, when detection loss
occurs, has received little attention. In this paper, we investigate
a way of mitigating the effect of detection loss in VSNN systems.
In our approach detection losses are modeled as a Bernoulli
random variable and integrated into the state space model of
the dynamic system. To mitigate the effect of detection loss,
we propose a variation of a Kalman filter, that artificially
inflates the measurement noise covariance when detection loss
occurs. The Kalman filter was implemented on a 6DOF robotic
manipulator with an eye-in-hand configuration with YOLOv5
as the object detection network. The results show, that the
proposed Kalman filter decreases the effects of detection losses
and significantly improves performance compared to having a
standard Kalman filter, and not having a state estimator at
all. The benefit of our approach is especially noticeable when
detection loss occurs frequently and for relatively long periods
of time
Original languageEnglish
Title of host publication2023 11th International Conference on Control, Mechatronics and Automation, ICCMA 2023
Number of pages6
PublisherIEEE
Publication date2023
Pages1-6
Article number10375025
ISBN (Electronic)979-8-3503-1568-4
DOIs
Publication statusPublished - 2023
Event2023 11th International Conference on Control, Mechatronics and Automation (ICCMA) - Grimstad, Norway
Duration: 1 Nov 20233 Nov 2023

Conference

Conference2023 11th International Conference on Control, Mechatronics and Automation (ICCMA)
Country/TerritoryNorway
CityGrimstad
Period01/11/202303/11/2023
SeriesInternational Conference on Control, Mechatronics and Automation
ISSN2837-5149

Keywords

  • Visual servoing Detection loss Convolutional Neural Network YOLOv5 Estimation Kalman filter

Fingerprint

Dive into the research topics of 'Optimal State Estimation for DNN Visual Servoing Systems with Detection Loss'. Together they form a unique fingerprint.

Cite this