AutoDRRT is an autonomous driving framework developed based on the Autoware open-source framework, with targeted optimizations for the EIS400 onboard domain controller. These optimizations enhance the framework's real-time performance, distributability, and fault tolerance. A set of tools is provided to facilitate users in making use of these new features more easily. This framework is built upon the Robot Operating System 2 (ROS2). It encompasses all necessary functionalities from localization and target detection to path planning and control, striving to lower the entry barrier and aiming to involve as many individuals and organizations as possible in the open innovation of autonomous driving technology.

Based on the AutoDRRT framework, IEI secured the dual championship in both simulation and real vehicle races at the 5th Japan Automotive AI Challenge. This solution is tailored for factory scenarios and provides a Level 4 autonomous driving solution.

• Distributed

This framework supports transforming single-node applications into distributed applications with zero code changes.

• Enhanced Real time performance

  Significant Reduction in End-to-End Latency Achieved Through Multi-Faceted Optimization Strategies and Hardware-Software Co-design. The test data corresponds to the 'logging_simulator' scenario used in the Autoware framework

• Fault Tolerance

The framework supports concurrent startup of multiple identical algorithm nodes, capable of receiving and processing data simultaneously. In the event of a primary node failure due to faults, backup nodes seamlessly take over data transmission with millisecond-level switchover time.

• DDS integrated with DMA acceleration

The framework has upgraded Cyclone DDS, leveraging the DMA capabilities of Orin for shared memory implementation, thereby enhancing the transfer performance of large data blocks. The comparison between DDS and DDS integrated with DMA

• Unmanned Car Scenario

The framework supports unmanned car scenarios, capable of addressing obstacles, smoke, S-curves, L-curves, and other situations. It possesses safety, availability, and drivability.

The target platforms for AutoDRRT are as follows. There might be changes in future versions of AutoDRRT.

The AutoDRRT Foundation provides support only for the platforms listed below. Other platforms are not supported.

• amd64

    Recommend: X86 + NVIDIA GPU (4GB RAM)
  

• arm64

    Recommend: NVIDIA Orin OR NVIDIA Xavier
  

• EIS400

• NVIDIA Orin

• 8-core CPU

• 16GB RAM

• NVIDIA GPU (4GB RAM)

Docker ensures that all developers in the project have a consistent development environment. It is recommended for beginners, temporary users, and those unfamiliar with Ubuntu.

• Installation Method

• Environmental Requirements

  • Ubuntu 22.04

• Installation Method

Usage Instructions

If you want to use the unmanned car scenario on the current branch, please use the following command:

bash factory_scene.sh

[email protected]