Kalman Filter for Robot Vision: A Survey

TLDR

Kalman filters, with over 20 variants, have become central to robotic vision, addressing a wide range of tasks from perception and control to mapping and exploration, and have attracted extensive research attention. This review surveys recent developments in robot vision using Kalman filters, summarizing reports to facilitate easy referral to suitable methods. Kalman filters, including extended and unscented variants, address uncertainties in localization, navigation, tracking, motion control, visual servoing, and structure reconstruction from image sequences. The review notes that roughly 800 publications over the past 30 years demonstrate the effectiveness of Kalman filters in solving robot vision problems.

Abstract

Kalman filters have received much attention with the increasing demands for robotic automation. This paper briefly surveys the recent developments for robot vision. Among many factors that affect the performance of a robotic system, Kalman filters have made great contributions to vision perception. Kalman filters solve uncertainties in robot localization, navigation, following, tracking, motion control, estimation and prediction, visual servoing and manipulation, and structure reconstruction from a sequence of images. In the 50th anniversary, we have noticed that more than 20 kinds of Kalman filters have been developed so far. These include extended Kalman filters and unscented Kalman filters. In the last 30 years, about 800 publications have reported the capability of these filters in solving robot vision problems. Such problems encompass a rather wide application area, such as object modeling, robot control, target tracking, surveillance, search, recognition, and assembly, as well as robotic manipulation, localization, mapping, navigation, and exploration. These reports are summarized in this review to enable easy referral to suitable methods for practical solutions. Representative contributions and future research trends are also addressed in an abstract level.