RELEASE.md
Apollo 8.0 introduced the concept of package management for user learning scenarios, making it easier and faster for users to deploy and use Apollo. With Apollo 9.0, we enabled users to more easily perform secondary development on top of Apollo through Package Management 2.0, allowing them to easily build their own autonomous driving applications. Apollo 10.0 focused on a comprehensive upgrade for large-scale scenario-based applications. In terms of performance, it optimized the performance and stability of various levels and modules, and provided rich tools to improve optimization efficiency. Apollo 11.0 focuses on the large-scale deployment of functional autonomous vehicles in high-value scenarios, comprehensively upgrading perception, localization, planning, and development toolchains, significantly lowering the hardware and software development threshold, and helping developers efficiently build end-to-end autonomous driving operating systems.
Apollo 11.0 is tailored for high-value scenarios such as package delivery, street sweeping, security patrol, and campus shuttle services, unlocking critical capabilities including:
Apollo 11.0 fully supports an end-to-end automated workflow:
Vehicle Preparation → Route Planning → Autonomous Driving → Task Execution (e.g., cleaning, retail, passenger transport) → Anomaly Handling / Manual Takeover → Return-to-Depot Parking
Through tight hardware-software co-design and a comprehensive ecosystem of developer tools, Apollo 11.0 significantly lowers the R&D barrier and deployment cost for functional autonomous vehicles, accelerating their commercialization and large-scale adoption.
In Apollo 8.0, the concept of package management tailored for user learning scenarios was introduced to enable users to deploy and use Apollo more conveniently and efficiently. In Apollo 9.0, the package management tool was updated to Version 2.0, making it easier for users to conduct secondary development and effortlessly build their own autonomous driving applications based on Apollo. In Apollo 10.0, we realize that autonomous driving cannot remain at the stage of local validation. Instead, it requires a comprehensive upgrade, and needs to be applied to scenarios on a large scale. In terms of performance, the performance and stability of various layers and modules are optimied, and extensive tools are provided to improve optimization efficiency. At the cost level, the hardware costs are recuded by enriching the hardware ecosystem which provides users with more options. Besides, the software development costs are lowered by upgrading the operating system, establishing communication with other frameworks, and reusing ecological software capabilities. Regarding safety, functional safety strategies and functional safety framework capabilities are reinforced.
Better performance and enhanced stability to comprehensively reinforce Apollo's autonomous driving capabilities
Stronger capabilities, More various ecological support to significantly reduce R&D costs for both software and hardware
Comprehensive Safety Coverage for More Stable and Reliable Autonomous Driving
Apollo Open Source Platform 9.0 further focuses on enhancing the development and debugging experience, dedicated to provide autonomous driving developers with a unified development tool platform and easy-to-extend PnC and perception software framework interfaces. The new version reshapes the PnC and perception extension development method based on package management. It optimizes component splitting and configuration management according to business logic, simplifying the process of calling. In addition to the component extension method, a more lightweight plugin extension method has been added, simplifying the process of extending. The new version introduces Dreamview Plus, a brand-new developer tool that introduces modes for convenient multi-scenario use, a panel layout customizing visualization, and a resource center providing richer development resources. Furthermore, the LiDAR and Camera detection models in the new version have been upgraded for improved results, and incremental training methods have been opened up for easy extension. At the same time, support for 4D millimeter-wave radar has been added. Finally, the new version is adapted to the ARM architecture, and supports compilation and running on Orin, providing developers with additional device options.
PnC Extension Development Pattern Based On Package Management
Perception Extension Development Pattern Based On Package Management
Brand New Dreamview Plus Developer Tool
Fully Upgraded Perception Model to Support Incremental Training
[Note] All models and methodologies included in Apollo 9.0 are for research purposes only. Productized and commercialized uses of these models are NOT encouraged, and it is at your own risk. Please be cautious to try Apollo 9.0 with sufficient safety protection mechanisms in place. Your feedback is highly appreciated so that we can continuously improve the models.
Apollo 8.0 is an effort to provide an extensible software framework and complete development cycle for Autonomous Driving developer. Apollo 8.0 introduces easily-reused Package to organize software modules. Apollo 8.0 integrates the whole process of perception development ,by combining model training service, model deployment tool and end-to-end visual validation tool . And another 3 new deep learning models are incorporated in Apollo 8.0 for perception module. Simulation service is upgraded by integrating local simulator in Dreamview to provide powerful debug tool for PnC developer.
[Note] All models and methodologies included in Apollo 8.0 are for research purposes only. Productized and commercial uses of these models are NOT encouraged, and it is at your own risk. Please be cautious to try Apollo 8.0 with enough safety protection mechanism. Your feedback is highly appreciated for us to continuously improve the models.
Apollo 7.0 incorporates 3 brand new deep learning models to enhance the capabilities for Apollo Perception and Prediction modules. Apollo Studio is introduced in this version, combining with Data Pipeline, to provide a one-stop online development platform to better serve Apollo developers. Apollo 7.0 also publishes the PnC reinforcement learning model training and simulation evaluation service based on previous simulation service.
[Note] All models and methodologies included in Apollo 7.0 are for research purposes only. Productized and commercial uses of these models are NOT encouraged, and it is at your own risk. Please be cautious to try Apollo 7.0 with enough safety protection mechanism. Your feedback is highly appreciated for us to continuously improve the models.
Apollo 6.0 incorporates new deep learning models to enhance the capabilities for certain Apollo modules. This version works seamlessly with new additions of data pipeline services to better serve Apollo developers. Apollo 6.0 is also the first version to integrate certain features as a demonstration of our continuous exploration and experimentation efforts towards driverless technology.
[Note] All models and methodologies included in Apollo 6.0 are for research purposes only. Productized and commercial uses of these models are NOT encouraged, and it is at your own risk. Please be cautious to try Apollo 6.0 with enough safety protection mechanism. Your feedback is highly appreciated for us to continuously improve the models.
Apollo 5.5 enhances the complex urban road autonomous driving capabilities of previous Apollo releases, by introducing curb-to-curb driving support. With this new addition, Apollo is now a leap closer to fully autonomous urban road driving. The car has complete 360-degree visibility, along with upgraded perception deep learning model a brand new prediction model to handle the changing conditions of complex road and junction scenarios, making the car more secure and aware. New Planning scenarios have been introduced to support curb-side functionality.
Vehicles with this version can drive autonomously in complex urban road conditions including both residential and downtown areas. BE CAUTIOUS WHEN DRIVING AUTONOMOUSLY, ESPECIALLY AT NIGHT OR IN POOR VISION ENVIRONMENT. URBAN DRIVING INVOLVES NAVIGATING HIGH RISK ZONES LIKE SCHOOLS, PLEASE TEST APOLLO 5.0 WITH THE SUPPORT FROM APOLLO ENGINEERING TEAM, PLEASE AVOID DRIVING THE VEHICLE ON THE HIGHWAY OR AT SPEEDS THAT ARE ABOVE OUR SUPPORTED THRESHOLD.
Apollo 5.0 is an effort to support volume production for Geo-Fenced Autonomous Driving. The car now has 360-degree visibility, along with upgraded perception deep learning model to handle the changing conditions of complex road scenarios, making the car more secure and aware. Scenario-based planning has been enhanced to support additional scenarios like pull over and crossing bare intersections.
Vehicles with this version can drive autonomously in complex urban road conditions including both residential and downtown areas. BE CAUTIOUS WHEN DRIVING AUTONOMOUSLY, ESPECIALLY AT NIGHT OR IN POOR VISION ENVIRONMENT. URBAN DRIVING INVOLVES NAVIGATING HIGH RISK ZONES LIKE SCHOOLS, PLEASE TEST APOLLO 5.0 WITH THE SUPPORT FROM APOLLO ENGINEERING TEAM, PLEASE AVOID DRIVING THE VEHICLE ON THE HIGHWAY OR AT SPEEDS THAT ARE ABOVE OUR SUPPORTED THRESHOLD.
Apollo 3.5 is capable of navigating through complex driving scenarios such as residential and downtown areas. With 360-degree visibility and upgraded perception algorithms to handle the changing conditions of urban roads, the car is more secure and aware.
Vehicles with this version can drive autonomously in complex urban road conditions including both residential and downtown areas. BE CAUTIOUS WHEN DRIVING AUTONOMOUSLY, ESPECIALLY AT NIGHT OR IN POOR VISION ENVIRONMENT. URBAN DRIVING INVOLVES NAVIGATING HIGH RISK ZONES LIKE SCHOOLS, PLEASE TEST APOLLO 3.5 WITH THE SUPPORT FROM APOLLO ENGINEERING TEAM.
Apollo 3.0 enables L4 product level solution that allows vehicles to drive in a closed venue setting at a low speed. Automakers can now leverage this one stop solution for autonomous driving without having to customize on their own.
Vehicles with this version can drive autonomously in a Closed Venue setting. It is a production ready version for low-speed autonomous driving capabilities.
This release allows the vehicle to autonomously run on geo-fenced highways. Vehicles are able to do lane keeping cruise and avoid collisions with the leading vehicles.
Vehicles with this version can drive autonomously on highways at higher speed with limited HD map support. The highway needs to have clear white painted lane marks with minimum curvatures. The performance of vision based perception will degrade significantly at night or with strong light flares. BE CAUTIOUS WHEN DRIVING AUTONOMOUSLY, ESPECIALLY AT NIGHT OR IN POOR VISION ENVIRONMENT. PLEASE TEST APOLLO 2.5 WITH THE SUPPORT FROM APOLLO ENGINEERING TEAM.
This release supports that vehicles autonomously drive on simple urban roads. Vehicles are able to cruise and avoid collisions with obstacles, stop at traffic lights and change lanes if needed to reach the destination.
modules/toolsVehicles with this version can drive autonomously on simple urban roads with light to medium traffic at slow to medium speed.
This release supports that vehicles autonomously cruise on fixed lanes.
modules/tools/Vehicles with this version do NOT detect traffic lights. Vehicles will NOT stop at red traffic lights. Neither will they change lanes on the road.
Initial release of Apollo implements autonomous GPS waypoint following.
modules/tools/Vehicles with this version do NOT perceive obstacles in close promixity. Neither can they drive on public roads or areas without GPS signals.