arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.12886cs.ROcs.CVcs.NE
收藏

基于深度学习图像理解技术的自主无人机控制设计

Control Design of Autonomous Drone Using Deep Learning Based Image Understanding Techniques

The University of Sydney(悉尼大学)

Seid Miad Zandavi, Vera Chung, Ali Anaissi

摘要:

本文提出了一种新的框架,使用图像作为输入的控制器有自主飞行,考虑到嘈杂的室内环境和不确定性。提出了一种新的具有导数滤波器的比例积分导数加速(PIDA)控制,以提高无人机/四轴飞行器在噪声环境中的飞行稳定性,并使用对象和深度检测技术实现自主飞行。数学模型是从一个精确的模型,具有高度的保真度,通过解决非线性,不确定性和耦合的问题。提出的PIDA控制器的随机对偶单纯形算法(SDSA)调整,以支持自主飞行。仿真结果表明,将基于深度学习的图像理解技术(RetinaNet蚁群检测和PSMNet)应用于所提出的控制器,可以在存在环境干扰的情况下生成和跟踪所需点。

英文摘要:

This paper presents a new framework to use images as the inputs for the controller to have autonomous flight, considering the noisy indoor environment and uncertainties. A new Proportional-Integral-Derivative-Accelerated (PIDA) control with a derivative filter is proposed to improves drone/quadcopter flight stability within a noisy environment and enables autonomous flight using object and depth detection techniques. The mathematical model is derived from an accurate model with a high level of fidelity by addressing the problems of non-linearity, uncertainties, and coupling. The proposed PIDA controller is tuned by Stochastic Dual Simplex Algorithm (SDSA) to support autonomous flight. The simulation results show that adapting the deep learning-based image understanding techniques (RetinaNet ant colony detection and PSMNet) to the proposed controller can enable the generation and tracking of the desired point in the presence of environmental disturbances.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑