A ROS-based distributed multi-robot localization and orientation strategy for heterogeneous robots

Alajami, Abdussalam A.; Palau, Nil; Lopez-Soriano, Sergio; Pous Andrés, Rafael

doi:http://dx.doi.org/10.1007/s11370-023-00457-7

A ROS-based distributed multi-robot localization and orientation strategy for heterogeneous robots

License

Citation

Alajami AA, Palau N, Lopez-Soriano S, Pous R. A ROS-based distributed multi-robot localization and orientation strategy for heterogeneous robots. Intell Serv Robot. 2023;16(2):177-93. DOI: 10.1007/s11370-023-00457-7

Abstract

The problem of estimating and tracking the location and orientation of a mobile robot by another in heterogeneous distributed multi-robots is studied in this paper. We propose a distributed multi-robot localization strategy (DMLS) that is Robotic Operating System (ROS) based. It consists of an algorithm that fuses data of diverse sensors from 2 heterogeneous robots that are not connected within their transform trees to localize and measure the relative position and orientation. The method exploits the robust detection of the Convolutional Neural Networks (CNN) and the accurate relative position measurements from the local costmap. The algorithm is composed of two parts: The localization part and the relative orientation measurement part. Localization is done by optimization and alignment calibration of the CNN output with the costmap in an individual robot. The relative orientation measurement is done by a collaborative multi-robot fusing of diverse sensor data to align and synchronize the transform frames of both robots in their costmaps. To illustrate the performance of this strategy, the proposed method is compared with a conventional object localization and orientation measuring method that uses computer vision and QR codes. The results show that this proposed method is robust and accurate while maintaining a degree of simplicity and efficiency in costs. The paper also presents various application experiments in laboratory and simulation environments. By using the proposed method, distributed multi-robots collaborate to achieve collective intelligence from individuals, which increases team performance.