Work

A concurrent learning approach to monocular vision range regulation of leader/follower systems

Year: 2024

Type: book-chapter

Abstract: This paper explores range and bearing angle regulation of a leader–follower using monocular vision. The main challenge is that monocular vision does not directly provide a range measurement. The contribution is a novel concurrent learning (CL) approach, called CL Subtended Angle and Bearing Estimator for Relative pose (CL-SABER), which achieves range regulation without communication, persistency of excitation or known geometry and is demonstrated on a physical, robot platform. A history stack estimates target size which augments the Kalman filter (KF) with a range pseudomeasurement. The target is followed to scale without drift, persistency of excitation requirements, prior knowledge, or additional measurements. Finite excitation is required to achieve parameter convergence and perform steady-state regulation using CL-SABER. Evaluation using simulation and mobile robot experiments in special Euclidean planar space (SE(2)) show that the new method provides stable and consistent range regulation, as demonstrated by the inter-rater reliability, including in noisy and high leader acceleration environments.

Source: Autonomous Robots

DOI: 10.1007/s10514-024-10178-0

Authors: Luisa Fairfax, Patricio Vela

Institutions: DEVCOM Army Research Laboratory, United States Army Combat Capabilities Development Command, Georgia Institute of Technology

Language: English

Topic: Advanced Vision and Imaging

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,690

Funders: National Science Foundation, DEVCOM Army Research Laboratory