PROJECT TITLE :
A Tradeoff Analysis of a Cloud-Based Robot Navigation Assistant Using Stereo Image Processing
The utilization of Cloud Computing for computation offloading in the robotics area has become a field of interest nowadays. The aim of this work is to demonstrate the viability of cloud offloading in a low level and intensive computing task: a vision-based navigation help of a service mobile robot. In order to do therefore, a prototype, running over a ROS-primarily based mobile robot (Erratic by Videre Design LLC) is presented. The information extracted from on-board stereo cameras will be employed by a personal cloud platform consisting of 5 bare-metal nodes with AMD Phenom 965 × 4 CPU, with the cloud middleware Openstack Havana. The particular task is the shared management of the robot teleoperation, that's, the graceful filtering of the teleoperated commands with the detected obstacles to stop collisions. All the doable offloading models for this case are presented and analyzed. Several performance results using completely different communication technologies and offloading models are explained moreover. Additionally to the present, a real navigation case during a domestic circuit was done. The tests demonstrate that offloading computation to the Cloud improves the performance and navigation results with respect to the case where all processing is completed by the robot.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here