Skip to content

Latest commit

 

History

History
88 lines (62 loc) · 2.88 KB

README.md

File metadata and controls

88 lines (62 loc) · 2.88 KB
Raw

Apollo ROS

Apollo is the most mature and sophisticated autonomous driving platform that is open source right now.

However, there are some limitations.

  • If you want to understand their code and test it with your own application, you will need to have a good understanding of their framework before you can make any modifications.
  • The rviz and rqt tools are absent or awkward to use

Have you wondered, what if everything can be run as a standard ROS node and you can use all the familiar tools that are available in ROS? Then this repository is what you need!

All contributions are welcome!! There are so many things that can be improved. Please raise issues and/or make pull requests if you would like to work on it too. Thank you.

cnnseg

Environment Information

You can build this project under CPU-Only machine(which only build those parts that do not depend on GPU).

The system is also tested on GPU machine including GeForce GTX 1080 Ti、RTX 2070 Super and RTX A4000 Laptop GPU. Please install Nvidia Driver, Docker, and nvidia-container-toolkit. The build process of docker image could reference to ubuntu18-cuda11.1-ros.Dockerfile. You can build the docker like this (the tag has been used in dev_start.sh, so if you changed tag below, the image name should also be modified in dev_start.sh).

cd docker/build
docker build -t nvidia/cuda:11.1-cudnn8-melodic-libtorch1.9.0 -f ubuntu18-cuda11.1-ros.Dockerfile .

Dependencies

Ubuntu 18.04
Nvidia Driver 470.86
CUDA 11.1
Cudnn 8.0.5
TensorRT 7.2.1
libtorch 1.9.0
cmake 3.20

Building and Running

  1. Clone Repository in Host
git clone https://github.com/Tartisan/apollo_ros
  1. Make ROS Packages
cd apollo_ros/
bash apollo.sh build
source devel/setup.bash
  1. Or use Docker
cd apollo_ros/
bash docker/scripts/dev_start.sh
bash docker/scripts/dev_into.sh
bash apollo.sh build
source devel/setup.bash
  1. rosrun the node you want to use
package node
perception perception_camera_node
perception perception_lidar_node (enclude: cnnseg, pointpilar)
drivers conti_radar
transform static_transform
data_conversion record_to_rosbag
data_conversion rosbag_to_record
sensor_visualizer viz_conti_radar
  1. rosbag for demo
bash scripts/republish.sh
rosbag play 20210823063212.bag

The bag can be downloaded at Baidu Netdisk, pwd: be9h

To Do:

  1. Add Drivers / Localization / Prediction / Planning / Control modules.