Development of an autonomous object transfer system by an unmanned aerial vehicle based on binocular vision. (27th February 2020)

• Record Type: Journal Article
• Authors: Liu, Xu; Chen, Bo; He, Yuqing; Li, Decai
• Is Part Of: International journal of advanced robotic systems. Volume 17:Number 1(2020:Jan./Feb.)
• Publication Date: 2020-02-27
• Subjects: Unmanned aircraft system -- vision-based perception -- navigation and control -- autonomous task; Robotics -- Periodicals; Robotics; Periodicals; 629.892
• DOI: 10.1177/1729881420907732
• Languages: English
• ISSNs: 1729-8806

Abstract

This article describes the development of an unmanned aerial vehicle system that had a remarkable performance in the 6th International Unmanned Aerial Vehicle Innovation Grand Prix, which was held on November 2–4, 2018, in Anji, China. The main mission of the competition was to build a simulated tower using prefabricated components by an unmanned rotorcraft, which could be decomposed into the following four subtasks: (1) navigation and control, (2) recognition and location, (3) grasp and construction, and (4) task planning and scheduling. All the tasks were required to perform autonomously without human intervention. According to the requirement of the mission, the unmanned aerial vehicle system was designed and implemented with high degree of autonomy and reliability, whose hardware was developed on a quadrotor platform by integrating various system components, including sensors, computers, power, and grasp mechanism. Software algorithms were exploited, and executable computer codes were implemented and integrated with the developed unmanned aerial vehicle hardware system. Integration of the two provided onboard intelligence to complete the mission. This article addresses the major components and development process of the unmanned aerial vehicle system and describes its applications to the competition mission.