openpilot

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system in 275+ supported cars.

49,706

9,038

49,706

166

View on GitHub

Top Related Projects

autoware

9,049

Autoware - the world's leading open-source software project for autonomous driving

autoware

9,050

Autoware - the world's leading open-source software project for autonomous driving

self-driving-car

6,227

The Udacity open source self-driving car project

Quick Overview

OpenPilot is an open-source driver assistance system developed by Comma.ai. It aims to provide advanced driver assistance features, including adaptive cruise control and lane keeping assistance, for a wide range of supported vehicles. OpenPilot is designed to be a safer and more accessible alternative to proprietary systems.

Pros

Open-source nature allows for community contributions and improvements
Supports a wide range of vehicle models
Continuously updated and improved
More affordable than many proprietary driver assistance systems

Cons

Requires additional hardware (Comma device) for installation
May void vehicle warranty if not installed properly
Limited to specific vehicle models and years
Requires technical knowledge for installation and maintenance

Code Examples

# Example 1: Accessing vehicle data
import cereal.messaging as messaging

sm = messaging.SubMaster(['carState'])
while True:
    sm.update()
    print(f"Vehicle speed: {sm['carState'].vEgo}")

This code snippet demonstrates how to access vehicle data using OpenPilot's messaging system.

# Example 2: Controlling lateral movement
from selfdrive.car.honda.interface import CarInterface

def apply_steer_torque(self, torque):
    can_sends = []
    apply_steer = int(torque)
    can_sends.append(CarInterface.create_steer_command(self, apply_steer, 1))
    return can_sends

This example shows how to apply steering torque in a Honda vehicle using OpenPilot's car interface.

# Example 3: Monitoring driver attention
from selfdrive.monitoring.driver_monitor import DriverStatus

driver_status = DriverStatus()
driver_status.get_pose(frame, driver_monitoring_params)
attention = driver_status.get_attention()

This code snippet demonstrates how to use OpenPilot's driver monitoring system to assess driver attention.

Getting Started

To get started with OpenPilot:

Check if your vehicle is supported: Supported Cars
Purchase a Comma device (e.g., Comma Three)
Install the Comma device in your vehicle following the provided instructions
Connect the device to your vehicle's OBD-II port
Follow the on-screen setup instructions to calibrate and configure OpenPilot

For developers:

git clone https://github.com/commaai/openpilot.git
cd openpilot
./tools/ubuntu_setup.sh

This will clone the repository and set up the development environment on Ubuntu. For more detailed instructions, refer to the README file in the repository.

Competitor Comparisons

autoware

9,049

Autoware - the world's leading open-source software project for autonomous driving

Pros of Autoware

More comprehensive, full-stack autonomous driving framework
Supports various sensor configurations and vehicle platforms
Stronger focus on research and development in autonomous driving

Cons of Autoware

Steeper learning curve and more complex setup
Less optimized for consumer-grade hardware
Requires more extensive testing and validation for real-world use

Code Comparison

Openpilot (Python):

def update(self):
  if self.sm.updated['carState']:
    self.v_cruise_kph = self.sm['carState'].cruiseState.speed * CV.MS_TO_KPH
    self.v_cruise_cluster_kph = self.sm['carState'].cruiseState.speedCluster * CV.MS_TO_KPH

Autoware (C++):

void update()
{
  auto msg = vehicle_state_pub_->msg_;
  msg->header.stamp = this->now();
  msg->velocity = current_velocity_;
  vehicle_state_pub_->publish(msg);
}

Both projects aim to provide autonomous driving capabilities, but Openpilot focuses on consumer vehicles with existing advanced driver-assistance systems, while Autoware offers a more flexible and comprehensive framework for various autonomous driving applications. Openpilot's codebase is primarily in Python, making it more accessible for rapid development, while Autoware uses C++ for better performance in complex autonomous driving scenarios.

autoware

9,050

Autoware - the world's leading open-source software project for autonomous driving

Pros of Autoware

More comprehensive, full-stack autonomous driving framework
Supports various sensor configurations and vehicle platforms
Stronger focus on research and development in autonomous driving

Cons of Autoware

Steeper learning curve and more complex setup
Less optimized for consumer-grade hardware
Requires more extensive testing and validation for real-world use

Code Comparison

Openpilot (Python):

def update(self):
  if self.sm.updated['carState']:
    self.v_cruise_kph = self.sm['carState'].cruiseState.speed * CV.MS_TO_KPH
    self.v_cruise_cluster_kph = self.sm['carState'].cruiseState.speedCluster * CV.MS_TO_KPH

Autoware (C++):

void update()
{
  auto msg = vehicle_state_pub_->msg_;
  msg->header.stamp = this->now();
  msg->velocity = current_velocity_;
  vehicle_state_pub_->publish(msg);
}

self-driving-car

6,227

The Udacity open source self-driving car project

Pros of self-driving-car

More comprehensive educational resource with a broader range of topics
Includes datasets and challenges for learning and experimentation
Community-driven with contributions from various developers and researchers

Cons of self-driving-car

Less actively maintained compared to openpilot
Not designed for direct implementation in real vehicles
Lacks a unified, production-ready codebase

Code Comparison

openpilot (Python):

def update(self):
  if self.sm.updated['carState']:
    self.v_cruise_kph = self.sm['carState'].cruiseState.speed * CV.MS_TO_KPH
    self.v_cruise_cluster_kph = self.sm['carState'].cruiseState.speedCluster * CV.MS_TO_KPH

self-driving-car (Python):

def process_image(image):
    yuv = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)
    yuv[:,:,0] = cv2.equalizeHist(yuv[:,:,0])
    return cv2.cvtColor(yuv, cv2.COLOR_YUV2RGB)

The code snippets demonstrate different focuses: openpilot deals with real-time vehicle data processing, while self-driving-car showcases image processing techniques for autonomous driving.

Convert designs to code with AI

Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.

Try Visual Copilot

README

openpilot

openpilot is an operating system for robotics.
Currently, it upgrades the driver assistance system in 275+ supported cars.

Docs Â· Roadmap Â· Contribute Â· Community Â· Try it on a comma 3X

Quick start: bash <(curl -fsSL openpilot.comma.ai)

To start using openpilot in a car

To use openpilot in a car, you need four things:

Supported Device: a comma 3/3X, available at comma.ai/shop.
Software: The setup procedure for the comma 3/3X allows users to enter a URL for custom software. Use the URL openpilot.comma.ai to install the release version.
Supported Car: Ensure that you have one of the 275+ supported cars.
Car Harness: You will also need a car harness to connect your comma 3/3X to your car.

We have detailed instructions for how to install the harness and device in a car. Note that it's possible to run openpilot on other hardware, although it's not plug-and-play.

To start developing openpilot

openpilot is developed by comma and by users like you. We welcome both pull requests and issues on GitHub.

Join the community Discord
Check out the contributing docs
Check out the openpilot tools
Read about the development workflow
Code documentation lives at https://docs.comma.ai
Information about running openpilot lives on the community wiki

Want to get paid to work on openpilot? comma is hiring and offers lots of bounties for external contributors.

Safety and Testing

openpilot observes ISO26262 guidelines, see SAFETY.md for more details.
openpilot has software-in-the-loop tests that run on every commit.
The code enforcing the safety model lives in panda and is written in C, see code rigor for more details.
panda has software-in-the-loop safety tests.
Internally, we have a hardware-in-the-loop Jenkins test suite that builds and unit tests the various processes.
panda has additional hardware-in-the-loop tests.
We run the latest openpilot in a testing closet containing 10 comma devices continuously replaying routes.

Licensing

openpilot is released under the MIT license. Some parts of the software are released under other licenses as specified.

Any user of this software shall indemnify and hold harmless Comma.ai, Inc. and its directors, officers, employees, agents, stockholders, affiliates, subcontractors and customers from and against all allegations, claims, actions, suits, demands, damages, liabilities, obligations, losses, settlements, judgments, costs and expenses (including without limitation attorneysâ fees and costs) which arise out of, relate to or result from any use of this software by user.

THIS IS ALPHA QUALITY SOFTWARE FOR RESEARCH PURPOSES ONLY. THIS IS NOT A PRODUCT. YOU ARE RESPONSIBLE FOR COMPLYING WITH LOCAL LAWS AND REGULATIONS. NO WARRANTY EXPRESSED OR IMPLIED.

User Data and comma Account

By default, openpilot uploads the driving data to our servers. You can also access your data through comma connect. We use your data to train better models and improve openpilot for everyone.

openpilot is open source software: the user is free to disable data collection if they wish to do so.

openpilot logs the road-facing cameras, CAN, GPS, IMU, magnetometer, thermal sensors, crashes, and operating system logs. The driver-facing camera is only logged if you explicitly opt-in in settings. The microphone is not recorded.

By using openpilot, you agree to our Privacy Policy. You understand that use of this software or its related services will generate certain types of user data, which may be logged and stored at the sole discretion of comma. By accepting this agreement, you grant an irrevocable, perpetual, worldwide right to comma for the use of this data.

Top Related Projects

Convert designs to code with AI

Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.

Try Visual Copilot