Skip to main content
Donkeycar is a minimalist and modular self-driving library for Python. It is developed for hobbyists and students with a focus on allowing fast experimentation and easy community contributions.

​
What is Donkeycar?

Donkeycar is being actively used at the high school and university level for learning and research. It offers a rich graphical interface and includes a simulator so you can experiment with self-driving even before you build a robot.
Donkeycar is designed to be the “Hello World” of autonomous driving - it is simple yet flexible and powerful.

​
Key Features

​
Modular Architecture

Donkeycar is built around a modular Vehicle and Parts architecture. A Donkeycar application is organized as a pipeline of software parts that run in order on each pass through the vehicle loop, reading inputs and writing outputs to the vehicle’s software memory. 
from donkeycar import Vehicle
from donkeycar.parts.cv import CvCam
from donkeycar.parts.tub_v2 import TubWriter
import time

# Define a vehicle to take and record pictures 10 times per second
V = Vehicle()

IMAGE_W = 160
IMAGE_H = 120
IMAGE_DEPTH = 3

# Add a camera part
cam = CvCam(image_w=IMAGE_W, image_h=IMAGE_H, image_d=IMAGE_DEPTH)
V.add(cam, outputs=['image'], threaded=True)

# Warmup camera
while cam.run() is None:
    time.sleep(1)

# Add tub part to record images
tub = TubWriter(path='./dat', inputs=['image'], types=['image_array'])
V.add(tub, inputs=['image'], outputs=['num_records'])

# Start the drive loop at 10 Hz
V.start(rate_hz=10)

​
Multiple Hardware Platforms

Donkeycar runs on various platforms:
  • Raspberry Pi (recommended on-board computer)
  • Jetson Nano (for more compute-intensive applications)
  • PC/Mac (for development and simulation)

​
Rich Hardware Support

A typical Donkeycar has parts that:
  • Get images from various camera types including standard cameras, 3D cameras, and lidar
  • Read GPS position from GPS receivers for path following
  • Accept user input from game controllers (PS3, PS4, Xbox, WiiU, Nimbus, Logitech) or RC controllers
  • Control drivetrain motors supporting various configurations:
    • ESC/Steering-servo (standard RC car)
    • Differential drive
    • H-Bridge motor drivers
  • Record telemetry data including camera images, steering/throttle inputs, lidar data, and more

​
Three Types of Autopilots

# Uses neural networks (TensorFlow, TensorFlow Lite, PyTorch)
# Learns from human driving data
# Supports multiple model architectures

​
Use Cases

​
DIY Robocars Racing

Compete in self-driving races like DIY Robocars, including online simulator races against competitors from around the world.
Donkeycar includes a built-in simulator so you can race virtually before building physical hardware.

​
Research and Education

Donkeycar is actively used in:
  • High school STEM programs
  • University research projects
  • Machine learning education
  • Robotics courses

​
Experimentation

Experiment with:
  • Autopilots and neural networks
  • GPS navigation
  • Computer vision algorithms
  • Sensor fusion

​
Community Learning

Participate in a vibrant online community learning cutting-edge technology and having fun doing it.

​
Prerequisites

TL;DR: No specific prerequisite knowledge is required to get started with Donkeycar!
However, it helps if you have some knowledge of:

​
Python Programming

You do not have to do any programming to use Donkeycar. The file you edit to configure your car, myconfig.py, is a Python file. You mostly just uncomment the sections you want to change and edit them.
Knowing how Python comments and indentation work helps avoid common mistakes.

​
Raspberry Pi

The Raspberry Pi is the preferred on-board computer for a Donkeycar. It is helpful to have set up and used a Raspberry Pi, but it is not necessary. You should be comfortable with:
  • Installing Raspberry Pi OS using Raspberry Pi Imager
  • Configuring the Raspberry Pi using raspi-config
  • Basic navigation and file operations

​
Linux Command Line

You will type commands into the terminal to install and start the Donkeycar software. Helpful skills include:
  • Navigating the file system
  • Listing, copying, and deleting files and directories
  • Remote access via SSH or VNC

​
Project Information

Current Version

v5.2.dev6

Python Version

Python 3.11

License

MIT License

Authors

Will Roscoe, Adam Conway, Tawn Kramer

​
Next Steps

Quick Start

Get started with your first autonomous car

Installation

Detailed installation instructions for your platform

Build docs developers (and LLMs) love

Get started for freeTalk to us