Cloudroid is a cloud robotic platform which supports the direct deployment of ROS software packages onto the cloud. Basically, it can be regarded as a PAAS platform which adopts the ROS application model. A ROS package can be covnerted into a cloud service automatically. The robotic applications can access the cloud service remotely in an on-demand style through a WebSocket protocol.
The service access is purely based on a cloud service paradigm, which means that you need not concern ROS master and other configurations. Multiple robots can access a service simultaneously, for example, to build their own map respectively. The robotic apllications which access the cloud services also need no modification, because Cloudrid can generate a stub ROS package with the same interface of the original ROS package, which acts as a local proxy of the remote cloud service.
By adopting the docker container technology in the back-end, a ROS package which is orignally designed for a single robot can serve multiple robots simultaneously by dynamically instantiation of the servant in the cloud. And by specifying the resource demand of the ROS package (e.g., mem, CPU, etc.), the quaility of a service can be assured by the internal mechanisms of Cloudroid.
Cloudroid is built and tested on Ubuntu 14.04, ROS indigo.
Since it currently based on Docker Swarm, Docker(https://docs.docker.com/engine/installation/linux/ubuntu/) must be installed on each host nodes.
Add user to the Docker group, logout and login again:
sudo addgroup $USER docker
docker swarm init docker run -d -p 5000:5000 --restart=always --name registry registry:2
sudo apt-get update sudo apt-get install python-dev python-pip python-tk git zip unzip sudo pip install pip --upgrade
git clone https://github.com/zhangpf/cloudroid cd Cloudroid/ git submodule update --recursive sudo pip install -r requirements.txt
base-imagedirectory, push it to the local docker registry:
cd base-image/ docker build . docker tag $(docker images -q | head -n1) ros:my docker tag ros:my localhost:5000/ros:my docker push localhost:5000/ros:my
cd .. python run.py