S1-PRO5-3 - A Comprehensive Experiment to Enhance Multidisciplinary Engineering Ability via UAVs Visual Navigation

1. Innovative Practice Work In Progress
Lu Li1 , Xiaoyan Luo1, Han Wan1, Chengxi Wu1, Yu Zheng1, Fugen Zhou1
1 Beihang University

Keywords: Multidisciplinary Engineering Ability; Comprehensive Experiment; UAVs Visual Navigation

Topics: Curriculum Design; Teaching & Learning Experiences in Engineering Education; Discipline Specific Issues: Aerospace Information Engineering

 Paper abstract (Work in Progress):

Aerospace engineering is a multidisciplinary subject which involves several different disciplines such as aircraft dynamics, control theory, navigation guidance, signal processing, telecommunication, and artificial intelligence. Therefore, it is highly desired to educate students in a multidisciplinary manner, so that they can systematically learn knowledge of different disciplines and integrate them together.  However, in the traditional curriculum setting, the related disciplines for aerospace engineering are independently distributed in different courses. Facing this challenge, this paper designs a comprehensive experiment based on Unmanned Aerial Vehicles (UAVs) Visual Navigation (UVN) to provide a multidisciplinary practice training environment for the students of the related professions. UVN is a multi-agent coordinated control platform for aerospace services, which includes UAVs aircraft, ground intelligent vehicle and multi-sensor systems. Based on it, the teacher could propose tasks that involve the related knowledge on aerospace, while the students could have the chance to explore the solution to the real problem with autonomously learning. In this UVN comprehensive experiment, the students are asked to realize an intelligent visual navigation system to track the free movement of the vehicle on the ground automatically. The multidisciplinary engineering ability runs through the whole process of the activities from data acquisition, conceptual design, to in-flight validation. For the first stage of data acquisition and processing, students need to learn how to capture images via various remote sensing collection devices, acquire the motion information to calculate the position and trajectory for the AVUs, and use image processing to identify the vehicle. In the second stage of simulation, the data and information acquired by the first stage can be used to conceptual design and simulate the possible solution on the Matlab/Simulink environment. Then, in the in-flight validation stage, the sub-models (signal transmission, real-time processing, dynamic system control, and automatic navigation) should be deliberately considered and efficiently combined together to realize the automatic control and autonomous visual navigation. The teacher works closely with the students, acting as a mentor and providing appropriate research advice, feedback and guidance to the students and ensuring that all engaged fully with the assigned tasks. Besides, all the teachers and the students are umpires in our course. Through the project demonstration and presentation at the end of the experiment, the multidisciplinary engineering ability of each student can be effectively evaluated. The UVN comprehensive experiment enables students to work on real-world engineering problems through a hardware-software integration framework, which may greatly stimulate their curiosity and interest in autonomously learning. It also provides students unprecedented opportunities to immerse themselves in projects that cross disciplinary boundaries, improve their professional ability and enhance their exploration competence in aerospace areas.