Project

# Title Team Members TA Documents Sponsor
32 Autonomous Target-Following Quadcopter with Real-Time YOLO Vision and Custom Flight Controller
Jintu Guo
Renang Chen
Zhenbo Chen
Zhengyu Zhu
proposal1.pdf
Lin Qiu
# Problem

Small unmanned aerial vehicles (UAVs) are widely used in applications such as aerial filming, search-and-rescue, and surveillance. However, most consumer-grade FPV (First Person View) drones rely entirely on manual control and lack the ability to autonomously track moving targets. We aim to design an autonomous target-following quadcopter system that leverages edge computing for real-time object detection. The drone needs to recognize a specific target using a vision system and autonomously follow it while maintaining stable flight, bridging the gap between manual FPV drones and expensive enterprise autonomous platforms.

# Solution Overview

Our solution consists of a custom-built 5-inch quadcopter (using a Mark frame, 2207 brushless motors, and 55A ESCs) equipped with an Orange Pi 5 as the central vision processor, and a custom-designed Flight Controller PCB. The Vision Subsystem on the Orange Pi 5 will run a YOLO object detection model to capture and identify the target's relative position. This spatial data is sent to our custom Flight Control Subsystem (STM32-based), which executes a closed-loop PID control algorithm to adjust the drone's attitude and thrust. To meet the high power demands of the vision board, the Power Subsystem—integrated into our custom PCB—will feature an optimized three-level buck converter to safely and efficiently step down the high-voltage LiPo battery to a stable 5V/4A supply. A Remote Control Subsystem will allow FPV manual override and mode switching.

# Solution Components

## Power Subsystem
A custom PCB integrating an advanced three-level buck converter. It steps down the voltage from a high-capacity LiPo battery (sized appropriately to target a 15-minute flight time) to provide a stable, low-ripple 5V/4A power supply for the Orange Pi 5, while routing raw power to the 55A Electronic Speed Controllers (ESCs).

## Flight Control Subsystem
The core of our custom PCB, built around an STM32 microcontroller and an IMU (e.g., MPU6000/BMI270). It receives tracking vectors from the Vision Subsystem and user inputs from the receiver, generating precise PWM signals for the ESCs to stabilize the drone and follow the target.

## Vision Subsystem
An Orange Pi 5 paired with a high-framerate camera module. It runs a YOLO-based object detection algorithm to process video feeds in real-time, computing the bounding box and relative spatial coordinates of the target object.

## Remote Control & Interaction Subsystem
A wireless FPV radio receiver link that allows the operator to manually control the drone, monitor telemetry, and safely toggle between manual FPV flight mode and autonomous tracking mode.

# Criterion for Success

- The custom three-level buck converter on the PCB can stably output 5V at 4A under continuous load, and sustain a peak current of 5A for up to 10 minutes without requiring additional active cooling or resetting the Orange Pi 5.
- The Vision Subsystem (Orange Pi 5) successfully runs the YOLO model at a minimum of 30 FPS to detect and output the relative coordinates of a target.
- The flight controller can smoothly process vision data to autonomously follow a target moving at a walking pace (1-2 m/s), keeping the target within the camera's field of view for at least 15 seconds.
- The customized power distribution and selected LiPo battery support a continuous flight/hover time approaching 15 minutes.
- The remote control system allows seamless switching between autonomous tracking and manual FPV override with a control latency of less than 300 ms.

# Distribution of Work

- **Zhenbo Chen (EE):** Power Subsystem design. Responsible for the custom PCB schematic and layout of the high-efficiency three-level buck converter and power distribution to the ESCs.
- **Zhengyu Zhu (EE):** Flight Control Subsystem design. Responsible for the STM32 integration on the custom PCB, IMU sensor fusion, and embedded PID flight control firmware.
- **Renang Chen (ECE):** Hardware Assembly and Systems Integration. Responsible for the Mark frame mechanical build, 2207 motor/55A ESC integration, battery sizing/testing, and Remote Control Subsystem configuration.
- **Jintu Guo (ECE):** Vision Subsystem design and implementation. Responsible for configuring the Orange Pi 5, deploying the YOLO model, and writing the serial communication protocol to send coordinate vectors to the STM32.

# Justification of Complexity

We believe our project possesses the significant electrical and embedded systems complexity required for ECE 445. The hardware core of this project is a highly complex custom PCB that must integrate a sensitive STM32 flight controller alongside a high-current, high-efficiency three-level buck converter. Delivering a clean 5V/4A to the Orange Pi 5 in an extremely noisy FPV drone environment (caused by 55A ESCs and high-KV 2207 motors) requires rigorous PCB layout, impedance matching, and thermal management skills. Furthermore, developing the embedded C firmware on the STM32 to bridge FPV radio inputs with autonomous YOLO-derived spatial vectors from a Linux board involves advanced knowledge of control theory, sensor fusion, and real-time communication protocols.

VTOL Drone with Only Two Propellers

Yanzhao Gong, Jinke Li, Tianqi Yu, Qianli Zhao

Featured Project

# **TEAM MEMBERS:**

- Yu Tianqi(tianqiy3)

- Li Jinke(jinkeli2)

- Gong Yanzhao(yanzhao8)

- Zhao Qianli(qianliz2)

# **TITLE: VTOL DRONE WITH ONLY TWO PROPELLERS**

# **PROBLEM:**

Nowadays, drones, as an important carrier of new technology and advanced productivity, have become an vital part of the development of new aviation forms. They have been used in many different areas such as military, civilian, commercial and so on. Traditional drones like helicopters have shortcomings in flight speed while fixed-wing aircraft require a runway for takeoff and landing. Vertical takeoff and landing (VTOL) aircraft not only have helicopters' assessibility and flexbility to take off and land in small spaces, thus they can fly to destinations that are not easily accessible by traditional aircraft, such as remote areas or areas with poor infrastructure; the design of VTOL also allows for faster deployment and response times which is especially important in emergency situations where every second counts. Addtionlly, simpler construcrtion of this drone not only reduces over all cost but requires less energy in longer flight time. Overall, VTOL aircraft offer a level of flexibility and efficiency that traditional aircraft cannot match, making them a valuable tool in a variety of industries, including transportation, military, and emergency services.

# **SOLUTION OVERVIEW:**

We plan to design a small VTOL UAV with a wingspan of about one meter to achieve both vertical takeoff and landing and horizontal flight like a fixed-wing aircraft by means of a horizontal tail and rotatable propellers located at the ends of the mean wings. Such two flight modes and the transition between them require a very precise perception and adjustment of the aircraft's attitude. To do this, we need a high frequency motherboard and some gyroscopic sensors to receive and process the aircraft attitude information and make feedback adjustments. This places high demands on the control section, and also on the mechanical side to ensure structural rigidity, reduce unpredictable jitter in the wings and other components, and thus reduce additional attitude adjustments. What's more, we also need to give more thought to the design of the rotatable propeller section. It is important to reduce the inertia of the rotating part while reducing the complexity of the structure and making it more reliable. For our aircraft, the arrangement of internal electronics and storage space has a huge impact on the center of gravity. While designing the aircraft structure with sufficient strength. We also consider the arrangement of the location of each electronic component, the heat dissipation of electronic components, sufficient storage space, certain water resistance, easier maintenance, etc. We believe that with the cooperation of the team members from different disciplines, we can be responsible for our own sub-projects and take full consideration of the design of other sub-projects to complete the overall design.

# **SOLUTION COMPONENTS:**

**VTOL Control Subsystem:** Different from the traditional sliding mode, vertical takeoff and landing makes our drone basically get rid of the dependence on the runway. This subsystem uses the GY-521 breakout of the MPU6050 6 degree of a freedom IMU. It gives adequate measurement precision to stabilize our drone. We use Teensy 4.0 as our microcontroller and use it for robotics, audio projects and Arduino applications (Teensyduino in our drone). After we assemble all the hardware stuff, we need to write the control code in Arduino/C++ language and uploaded them to the Teensy 4.0 board using Arduino IDE. Our drone will use the rotary lift fan to realize the vertical takeoff and landing of the aircraft by relying on the torque force output of the motor according to the feedback information of the IMU.

**Power Subsystem:** The power system will provide sufficient power for the takeoff and subsequent flight of the drone. It mainly includes two motors, two electric regulators, two propellers and batteries. In our VTOL drone, we plan to use Sunnysky brushless motors V2216, KV800, which could provide a maximum force of 1360N each. And according to the working current, we choose 30A electric regulators and 7.4V batteries.

**Mechanical Subsystem:** This system is the main structure of the drone, housing the rest subsystems of the drone. It is also a vital part, providing lift force when the drone is level. It consists of wings, fuselage and tail. In our drone, we plan to use lightweight PLA to 3D print the wings and other small part and laser cut the glass fiber plate to get the fuselage. Carbon fiber rods are also used in the wing parts to support the 3D printed wings.

**Adjustment of the center of gravity Subsystem:** This subsystem consist of a gyroscope and Teensy 4.0 board, which detects the position of the drone's center of gravity in real time and tranmits the information to the board. The board calculates and transmits the porper angle to the servos, so that the drone can fly soomthly in the air.

**Feedback Control Subsystem:** This subsysteem is aimed to ensure the drone mantains a stable flight path and does not deviate from its target orientation. The system works by comparing the current and target orientation and adjusting each propeller's angle according in order toreduce any error. A PID controller is used to determine the necessary adjustments, and it is then sent to the properllers via a servo motor in order to adjust the blades angles. This process is repeated contiually as the drone is flown.

**Flight mode adjustment Subsysytem:** This subsystem contains two servo, Teensy4.0 board, drone remote control and receiver. When the UAV recives a signal to switch from vertical flight mode to horizontal flight mode, it turns the angles od servos so that a horizontal force is generated to move the UAV in the horizontal direction.

# **CRITERION FOR SUCCESS:**

- Flight performance: The drone should be able to take off and land vertically, as well as hover and maneuver smoothly in the air. It should also have a sufficient range and flight time to perform its intended function.

- Payload capacity: The drone should be able to carry the required payload, such as a camera, sensors, or delivery package, while maintaining stability and flight performance.

- Safety: The drone should be designed with safety in mind, including proper wiring, motor placement, and redundancy systems to prevent crashes or malfunctions.

- Reliability: The drone should be built with high-quality components and tested thoroughly to ensure that it operates reliably and consistently over time.

- Cost-effectiveness: The drone should be designed and built in a cost-effective manner, using affordable components and minimizing unnecessary features or complexity.

# **DISTRIBUTION OF WORK**

## ME STUDENT Yanzhao Gong:

- Print and assembly the mechanical parts of the drone.

- Participate in the design of the rotating mechanism of the two propellerso and the follow-up improvement.

## EE STUDENT Qianli Zhao:

- Adjust and control the drone propellers angle when the drone goes from vertical takeoff to horizontal flight.

- Use the gyroscope to detect and adjust the center of gravity of the drone in time.

## ECE STUDENT Li Jinke:

- Participate in the electrical design of the drone. Complete the welding, assembly and debugging of the electronic control hardware equipment of drone

- Implementation and debugging of drone vertical takeoff and landing control algorithm code

## ME STUDENT Tianqi Yu:

- The design of the fuselage part of the structure, the use of glass fiber plate, carbon fiber rods and PLA 3d printing with the design of lightweight, high-strength fuselage.

- Participated in the design of the rotating mechanism of the two propellers at the end of the wing.