Skip to content

Chapter 1: Introduction and System Architecture

Intelligent Unmanned Systems (IUS), as an interdisciplinary integration of cutting-edge technologies—including artificial intelligence, machine vision, and swarm intelligence—serve as a concentrated embodiment of contemporary technological advancement. This chapter systematically reviews the foundational theoretical framework and control principles of intelligent unmanned systems, introduces the basic architecture of the RflySim toolchain, and outlines the assembly and calibration process of a multi-rotor drone, laying a solid theoretical and conceptual foundation for your subsequent in-depth learning.

1.1 Background and Theory

With the rapid development of cutting-edge technologies such as artificial intelligence, robotics, embodied intelligence, and autonomous driving, related concepts continue to emerge. Intelligent Unmanned Systems (IUS) build upon traditional unmanned systems by integrating artificial intelligence, endowing them with autonomous capabilities—including perception, reasoning, decision-making, and execution. Based on system scale and organizational complexity, IUS can be categorized into single-unit, formation, and swarm-cooperation systems, operating across underwater, terrestrial, and aerial platforms.

alt text

Despite the diversity of intelligent unmanned systems, their underlying concepts and architectures remain highly unified. Scientifically, they can be divided into six core modules: the airframe structure layer, the perception and localization layer, the control and decision-making layer, the actuation and execution layer, the environmental interaction layer, and the swarm collaboration layer. In spatial attitude estimation and control law design, the local navigation coordinate systems (NED / ENU) and the onboard front-right-down (FRD) coordinate system are widely adopted, with vehicle 3D spatial attitude precisely described using Euler angles or quaternions.

alt text

Taking multi-rotor drones as an example, a typical physical system comprises an airframe structure, a propulsion system (motors and propellers), a perception system (IMU and GNSS), an autopilot (flight control system), and a data link communication system. After assembly, the system must undergo rigorous steps—including firmware flashing, sensor calibration, power system testing, and field test flights—before it can be deployed for formal R&D experiments.

alt text alt text

1.2 Framework and Interfaces

The RflySim toolchain supports full-stack development—from low-level control filtering to high-level intelligent perception—and enables smooth transitions (Sim2Real) from pure-software simulation (SITL) to hardware-in-the-loop simulation (HITL) and real hardware deployment.

alt text

1.2.1 Overview of the RflySim Toolchain

RflySim is a professional, open, and research- and education-oriented simulation and development toolchain for intelligent unmanned systems. Adhering to the core principles of Model-Based Design (MBD) and full hardware-in-the-loop coverage, it provides developers with an integrated development framework supporting multi-rotor, fixed-wing, and unmanned ground vehicle platforms, and natively supports large-scale swarm distributed adversarial simulations involving over 100 nodes.

1.2.2 Core Components and Interfaces

The daily operation of RflySim relies on the collaboration of multiple software components: the core simulation engine is CopterSim, a kinematic simulation engine; high-fidelity visual and physical simulation environments are built upon Unreal Engine / RflySim3D; and mission planning and low-level monitoring are handled by the QGroundControl ground station.

For developers, the platform offers not only a firmware-level automatic code generation channel—PX4PSP—based on MATLAB/Simulink for low-level development, but also a rich set of Python / ROS interface libraries (RflySimSDK) for upper-layer AI validation and development.

alt text

This course begins with foundational system theory and software operation (Chapters 1–2), guiding you into the construction of high-fidelity 3D environments and mathematical models for various vehicle platforms (Chapters 3–4). After mastering low-level filter design and the core flight control closed-loop (Chapters 5–7), you will advance to high-level practical applications—including multimodal perception, visual mapping, and swarm coordination and game-theoretic adversarial scenarios (Chapters 8–10).

alt text

1.3 Showcase of Advanced Cases

alt text

alt text

alt text

alt text

alt text

alt text

alt text

Lecture recordings for this chapter:

1.5 Chapter Experiment Cases

The verification experiments and guided case studies related to this chapter are located in the [Installation Directory]\RflySimAPIs\1.RflySimIntro folder.

1.5.1 Interface Learning Experiments

Located in the 1.RflySimIntro\0.ApiExps folder, these experiments cover foundational platform interface tutorials and general introductions to each tool.

Experiment 1: Introduction to RflySim Toolchain Companion Textbooks

📝 Experiment Overview: Introduces companion textbook resources for the RflySim multirotor design and control platform, comprising 8 experimental tasks covering power systems, modeling, sensor calibration, filtering, and attitude control.

Experiment 2: PDF Document Collection and Merging Experiment

📝 Experiment Overview: Automates the collection, centralized archiving, and bookmarked merging of PDF documents across multiple experiment folders using Python, mastering the pathlib and pypdf libraries as well as natural sorting algorithms.

Experiment 3: Learning PX4 & Pixhawk Flight Control Systems

📝 Experiment Overview: Provides learning materials for the PX4 open-source autopilot system, QGroundControl ground station software, and MAVLink communication protocol, enabling users to master basic Pixhawk flight controller operations, firmware flashing, parameter configuration, and communication protocol development.

Experiment 4: Python Beginner's Tutorial

📝 Experiment Overview: Designed for absolute beginners, this experiment guides learners through 17 progressively structured tasks to systematically master core Python knowledge, including basic syntax, data structures, control flow, functions, library usage, file operations, exception handling, and object-oriented programming.

Experiment 5: MATLAB and Simulink Fundamentals Tutorial

📝 Experiment Overview: Introduces fundamental concepts and applications of MATLAB and Simulink, enabling users to acquire skills in control system design, data analysis, and algorithm development.

Experiment 6: Basic Functions and Usage of Visual Studio

📝 Experiment Overview: Covers basic features, installation and configuration, project management, and debugging techniques of the Microsoft Visual Studio integrated development environment.

Experiment 7: 3D Scene Construction Using 3Ds Max and Unreal Engine

📝 Experiment Overview: Introduces basic operations of 3Ds Max and Unreal Engine, enabling users to master 3D modeling, rendering, and scene construction skills, as well as understand their collaborative workflow.

Experiment 8: Fundamentals of Linux Operating Systems

📝 Experiment Overview: Introduces fundamental concepts, characteristics, and historical development of the Linux operating system, enabling users to master basic Linux system knowledge and operational skills.

Experiment 9: ROS Tutorial

📝 Experiment Overview: Covers fundamental concepts and installation/configuration of the Robot Operating System (ROS), and introduces the communication principles between MAVROS and the PX4 flight control system.

Experiment 10: RflySim Hardware System Configuration

📝 Experiment Overview: Introduces configuration methods for Pixhawk-series flight controllers (Pixhawk 2.4.8/6C/6X) and remote controllers (Tian Di Fei ET10, Foxer FS-i6S), helping users master fundamentals of drone hardware selection and assembly.

1.5.2 Basic Usage Experiments

Stored in the 1.RflySimIntro\1.BasicExps folder, these experiments provide a comprehensive set of supplementary instructional materials for beginners.

Experiment 1: Multicopter Design and Control Theory

📝 Experiment Overview: Learn multicopter design, dynamic modeling, state estimation, and control theory, covering fundamental knowledge in aerodynamics, motor circuits, and structural materials.

Experiment 2: Multicopter Design and Control Practice

📝 Experiment Overview: Conduct multicopter flight vehicle design and control experiments using the RflySim toolchain. This includes eight progressive experiments covering power system design, dynamic modeling, sensor calibration, filtering, attitude control, position control, semi-autonomous control, and fail-safe mechanisms, enabling mastery of the complete multicopter design and control workflow.

Experiment 3: Multicopter Flight Vehicle Design and Flight Experiment

📝 Experiment Overview: Study the textbook “Multicopter Flight Vehicles: From Principles to Practice”, mastering fundamental concepts, flight principles, and system composition of multicopters, as well as becoming familiar with setting up simulation environments and configuring parameters in the RflySim toolchain.

Experiment 4: Multicopter Flight Vehicle Remote Control Practice

📝 Experiment Overview: This experiment focuses on remote control techniques for multicopter drones, achieving communication between ground stations and flight vehicles via network protocols. It covers principles of flight attitude and position control, and uses the RflySim simulation platform to validate control algorithms.

Experiment 5: Small Fixed-Wing UAV Flight Control Practice

📝 Experiment Overview: A hands-on course on flight control for small fixed-wing UAVs. Through eight experiments covering UAV design, modeling, control, planning, and vision algorithms, it trains full-stack flight control development engineers using the RflySim toolchain.

Experiment 6: Python Fundamentals and VSCode Environment Setup

📝 Experiment Overview: Designed for beginners with no prior experience, this experiment teaches how to configure the VSCode editor and Python environment on the RflySim platform, enabling learners to read and modify example source code, and acquire basic code debugging skills.

Experiment 7: Drone Tracking a Ball Experiment

📝 Experiment Overview: Implement a complete pipeline for a drone to visually track a red ball using Python. Learners will study Python fundamentals—including syntax, data structures, control flow, functions—and learn to use the OpenCV image processing library, as well as master RflySim platform API usage and drone control methods.

Experiment 8: Linux System Fundamentals

📝 Experiment Overview: Introduce the characteristics, kernel versions, distributions, and file system structure of the Linux operating system, and guide learners through installing and using Ubuntu’s GUI and Windows WSL.

Experiment 9: Using WinWSL for Linux Command-Line Environment

📝 Experiment Overview: Learn to execute Python or shell scripts in an Ubuntu environment via WinWSL on Windows, enabling cross-platform development and seamless integration between Windows and Linux.

Experiment 10: Assembly and Debugging of a Quadcopter Drone

  • 📦 Version Requirement: Free Edition

    📝 Experiment Overview:
    Learn and master the assembly and tuning process of quadrotor UAVs, including the composition and functionality of core subsystems such as the airframe structure, power system, and flight control system. Study component selection, installation, and configuration methods, and acquire fundamental flight operation skills and safety protocols.

Experiment 11: Fixed-Wing UAV Assembly and Simulation

📝 Experiment Overview:
Introduce the fixed-wing UAV assembly process, covering three scenarios: Software-in-the-Loop (SIL) simulation, Hardware-in-the-Loop (HIL) simulation, and physical assembly. Learn to use the RflySim toolchain for fixed-wing UAV testing.

1.5.3 Advanced Development Experiments

Stored in the 1.RflySimIntro\2.AdvExps folder, these experiments further familiarize users with the configuration of certain low-level firmware ecosystems.

Experiment 1: Flight Controller ETH Port Configuration

📝 Experiment Overview:
Learn to configure the ETH port of Pixhawk V6X-series flight controllers as a MAVLink communication interface, enabling high-speed data communication between the flight controller and RflySim simulation software via Ethernet. Master network configuration techniques for multi-robot swarm simulation environments.

Experiment 2: RflySim Remote Controller Configuration

📝 Experiment Overview:
This experiment introduces the hardware configuration and usage of remote controllers on the RflySim platform, including configuration procedures for models such as the Foxeer FS-i6S, Tian Di Fei ET10, and Tian Di Fei AT9S Pro. Master the connection methods between remote controllers and computers, as well as communication protocol configuration, to ensure seamless communication and interaction between the remote controller and the RflySim toolchain.

Experiment 3: RflySim Toolchain Flight Controller Hardware Configuration

📝 Experiment Overview:
This experiment introduces hardware configuration methods for Pixhawk-series flight controllers on the RflySim platform, including firmware flashing, QGC parameter settings, and HIL simulation configuration. The goal is to master the setup of hardware-in-the-loop simulation environments.

Experiment 4: Feisi Swarm Simulation Unit ETH Port Configuration

📝 Experiment Overview:
Explain how to configure the ETH port of Pixhawk V6X flight controllers within the Feisi Swarm Simulation Unit to enable hardware-in-the-loop (HITL) simulation for up to 10 aircraft. Steps include router network configuration, flight controller firmware flashing, and automated parameter configuration using the NetSimAutoConfig.py script.

Experiment 5: Modifying PX4 Flight Controller Vehicle Frame via Ethernet Port

📝 Experiment Overview:
Use Python scripts and the MAVLink protocol to remotely modify the PX4 flight controller’s SYS_AUTOSTART parameter, switching the vehicle frame from quadrotor (1000) to fixed-wing (2100). Validate the configuration results using hardware-in-the-loop simulation, and master automated flight controller parameter configuration techniques.

Experiment 6: RflySim Python Development Environment Configuration

📝 Experiment Overview:
Learn how to configure the RflySim Python runtime environment in VSCode/PyCharm, and understand the principles of Python dependencies and the underlying API mechanisms.

Experiment 7: RflySim Platform Computer Hardware Requirements

📝 Experiment Overview:
Introduce the computer hardware requirements for running the RflySim platform, covering recommended configurations for three scenarios: smooth operation, full platform functionality, and flight controller development.

Experiment 8: RflySim UAV Hardware Configuration

📝 Experiment Overview: Learn the recommended configuration and usage methods for UAV hardware systems based on the RflySim platform, including assembly and debugging of the MindMotion MiniQuad 150 UAV development platform, and mastering hardware-in-the-loop simulation connection methods for flight controllers such as Pixhawk.

Experiment 9: Visual Studio Installation and Configuration

📝 Experiment Overview: Learn the installation and configuration of Visual Studio 2017 and 2022, and master the setup of the MATLAB Compiler environment to prepare for generating DLL files in the RflySim toolchain.

Experiment 10: Flight Controller Ethernet Simulation Configuration

📝 Experiment Overview: Learn how to configure the Ethernet simulation functionality of the Pixhawk 6x flight controller using the RflySim toolchain, and master the setup methods for flight controller network communication.

Experiment 11: WSL2 GPU Acceleration Configuration

📝 Experiment Overview: This experiment teaches how to configure GPU-accelerated computing in the WSL 2 environment, including CUDA toolkit installation, deployment of the PyTorch GPU version, GPU utilization within Docker containers, and performance validation—laying the foundation for GPU-accelerated simulation on the RflySim platform.

Experiment 12: ROS2 Shared Memory Zero-Copy Performance Validation

📝 Experiment Overview: Validate the performance advantages of ROS2 shared memory and zero-copy mechanisms in image transmission, comparing them with traditional network transmission methods to demonstrate reduced latency and decreased CPU resource consumption.

Experiment 13: WinWSL2-GPU Environment Installation and Configuration

📝 Experiment Overview: This experiment teaches how to install and configure a WSL 2 environment on Windows to support GPU acceleration. Students will learn the differences between WSL 1 and WSL 2, install GPU-accelerated environments such as CUDA and PyTorch, validate GPU acceleration functionality, test performance improvements in large matrix operations, and master both external installation and overlay installation methods.

Experiment 14: Local Deployment and Usage of Large Language Models

📝 Experiment Overview: Deploy the Ollama large language model service locally and offline in the WinWSL 2-GPU environment, and implement an end-to-end practical workflow for UAV mission control using the lightweight qwen3:0.6b model.

Experiment 15: QGC Log Download

📝 Experiment Overview: Download UAV flight logs using the QGroundControl ground station software, master log acquisition methods, and prepare for subsequent log analysis.

Experiment 16: Real-Time UAV Flight Status Acquisition Using Python

📝 Experiment Overview: Implement real-time acquisition and analysis of UAV flight logs using Python. Learn to use the mav.InitTrueDataLoop() interface to listen to ground-truth data (e.g., Euler angles, angular rates, velocity, position, etc.) and store and analyze the data.

Experiment 17: Real-Time UAV Flight Status Acquisition Using Simulink

  • 📦 Version Requirement: Free Edition

    📝 Experiment Overview:
    This experiment implements real-time acquisition, storage, and analysis of UAV flight logs using Simulink, covering both Software-in-the-Loop (SITL) and Hardware-in-the-Loop (HITL) simulations, and teaches methods for flight data acquisition and analysis.

Experiment 18: Custom uORB Message Logging

📝 Experiment Overview:
Records and analyzes controller variables (e.g., roll/pitch angles and angular rates) via custom uORB messages. The experiment comprises four steps: automatic code generation for firmware, HIL simulation, log download, and log parsing, aiding in controller performance optimization.

Experiment 19: Learning Flight Review Log Analysis

📝 Experiment Overview:
Uses the Flight Review website to learn UAV flight log analysis methods, focusing on attitude curve tracking performance and motor PWM output analysis, enabling evaluation of UAV flight performance and PID tuning status.

Experiment 20: CMD-Based Flight Log Analysis

📝 Experiment Overview:
Teaches how to convert .ulg flight log files into .csv format using the pyulog tool in a CMD environment, mastering fundamental flight log analysis techniques.

Experiment 21: MATLAB-Based Log Analysis

📝 Experiment Overview:
Teaches how to use RflySim’s ulog2csv function to convert .ulg logs to .csv format, and how to use the MATLAB Flight Log Analyzer application for flight log analysis, plotting attitude angle comparison charts, and saving figures.

Experiment 22: Python-Based Log Analysis

📝 Experiment Overview:
Teaches how to parse ULog-format flight control logs using Python, extract attitude data, and visualize comparisons between actual and desired values, mastering fundamental log analysis workflows and techniques.

Experiment 23: PlotJuggler-Based Log Analysis

📝 Experiment Overview:
Teaches how to use PlotJuggler software for UAV flight log analysis, covering log import, message data inspection, and graphical plotting of attitude angle curves.

Experiment 24: Binary Log Recording and Reading

📝 Experiment Overview:
Uses the binary_logger binary log module to write flight data to an SD card and perform reading/analysis, mastering the underlying log operation mechanism of the PX4 flight controller.

Experiment 25: Multi-UAV SIL Simulation Log Acquisition

📝 Experiment Overview:
Teaches automatic logging of .ulg-format logs during a 4-UAV SIL simulation, enabling analysis of UAV flight performance and behavior.

Experiment 26: configuring the Radiolink AT9S Pro Remote Controller

  • 📦 Version Requirement: Free Edition

    📝 Experiment Overview: Introduces the configuration method for the Radiolink AT9S Pro 12-channel transmitter, including multi-rotor mode setup, throttle reversal, channel mapping, and transmitter calibration, for drone flight control.

Experiment 27: FRSKY i6S Transmitter Configuration

📝 Experiment Overview: Introduces hardware configuration, functional interfaces, stick/switch operations, and status indicator usage for the FRSKY FS-i6S transmitter and FS-iA6B receiver, suitable for learning remote control of multi-rotor aircraft, FPV drones, and similar models.

Experiment 28: WELY ET10 Transmitter Configuration and Flight Mode Setup

📝 Experiment Overview: Introduces product features of the WELY ET10 transmitter and its calibration method for multi-rotor drones, including channel configuration for SA-SD, SE switches, and V1 knob, as well as switching and setup for three flight modes: Auto-stabilize, Altitude Hold, and Position Hold.

1.5.4 Advanced Development Experiments

No experiment cases available yet.