Design of a CloudROS enabled Mobile Robot
Qian Gao, Hongtai Cheng
- Year
- 2018
- Citations
- 3
Abstract
Mobile robot cannot work well when dealing with computation-intensive tasks because of its limited onboard computing and storage resources. The cloud robotics technology is able to solve this issue by expanding and offloading the robot's computations and data to the cloud. Most of the cloud robotics frameworks are compatible with ROS to fully utilize its rich packages and tool-sets. However, because of the interfacing and network structure problem, integrating cloud service to existing robot system usually requires much human effort. CloudROS is a cloud robotics framework which completely based on ROS and can be seamlessly integrated to ROS networks. All cloud services are provided as ROS nodes which can join the local robot's ROS network. The non-ROS protocols are masked by ROS service interface. In this paper, a mobile robot is designed to verify the effectiveness of the CloudROS architecture. The robot uses Raspberry Pi 3 as the main controller and microphone, stereo cameras to sense the world. The image processing, mapping building and navigation, human-robot interaction, data storing and remote monitoring functions are all realized through the cloud services. The experiments verify the effectiveness of the CloudROS framework and potentials of such a low-cost mobile robot.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002