应用神经网络作为直接控制器在全体无人机的位置和轨迹跟踪算法
Cezary Kownacki1, Slawomir Romaniuk2, Marcin Derlatka3
1Department of Automation of Manufacturing Processes, Bialystok University of Technology, 15-351, Białystok, Poland. c.kownacki@pb.edu.pl.
深度神经网络 (DNN) 为四旋翼控制提供高轨迹跟踪精度,优于其他神经网络. 更简单的模型为实时应用程序提供更低的延迟,平衡性能与特定的控制需求.
科学领域:
- 机器人技术 机器人技术 机器人技术
- 人工智能的人工智能
- 控制系统 控制系统
背景情况:
- 无人驾驶飞行器 (UAV),特别是四旋翼飞机,需要精确控制位置和轨迹跟踪.
- 传统的控制算法可能很复杂,并且可能并不总是能够最佳地适应动态飞行条件.
研究的目的:
- 评估各种神经网络架构作为用于四旋翼位置和轨迹跟踪的直接,独立的控制算法.
- 将不同神经网络的精度和计算性能与特定控制目标进行比较.
主要方法:
- 利用人工潜力现场方法来生成各种轨迹数据集用于培训和验证.
- 评估了单层回归网络,双层感知回归网络,深度神经网络 (DNN) 和残余网络 (ResNets).
- 评估了轨迹跟踪精度,使用根平均平方误差和皮尔森相关系数,以及计算延迟.
主要成果:
- 深度神经网络 (DNN) 在未经训练的场景中表现出卓越的轨迹跟踪精度 (RMSE 1.0830,R=0.9624) 和稳定的飞行.
- 像单层感知子这样的更简单的架构提供了显着较低的延迟,适合实时控制,尽管存在较小的准确性权衡.
- 在精度和延迟方面,ResNet架构表现不佳,这凸显了基于应用程序要求进行架构选择的必要性.
结论:
- 深度神经网络可以作为四旋翼位置跟踪的有效直接控制算法,当有足够的数据可用时,可能会取代传统方法.
- 该研究强调了准确性和延迟之间的权衡,建议针对特定无人机控制任务量身定制的神经网络选择.
- 基于神经网络的控制为无人机应用中实现高精度,可靠性和计算效率提供了有希望的方法.
更多相关视频
09:00Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect
Published on: December 19, 2016
07:49Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization
Published on: November 26, 2019
相关概念视频
One-Degree-of-Freedom System
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
Position Vectors
For instance, we want to locate a point P(x, y, z) relative to the origin of coordinates O. In that case, we can define a position...
Relative Motion Analysis using Rotating Axes-Problem Solving
Here, in order to determine the magnitude of velocity and acceleration for point...
Position and Displacement Vectors
Further, several important kinds of...
Hierarchy of Motor Control
Absolute Motion Analysis- General Plane Motion
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the...
