Loading [MathJax]/extensions/MathMenu.js
Performance Evaluation of Real-Time System for Vision-Based Navigation of Small Autonomous Mobile Robots | IEEE Conference Publication | IEEE Xplore

Performance Evaluation of Real-Time System for Vision-Based Navigation of Small Autonomous Mobile Robots


Abstract:

Real-time operation systems (RTOS) have become very important to the development of autonomous mobile robots. The choice of RTOS has tremendous sway with processor utiliz...Show More

Abstract:

Real-time operation systems (RTOS) have become very important to the development of autonomous mobile robots. The choice of RTOS has tremendous sway with processor utilization, response time, and real-time jitter. In this paper, we present experimental trials and analyze the feasibility of RTOS on a single-board computer for image recognition and vision-based navigation of small autonomous robot. Several real-time (RT) patches Linux frequently used not only in robotics are implemented and tested on the Raspberry Pi2 equipped with a native camera board. To study the speed of image recognition (classification) OpenCV library was used. Test results show that the RT Patch Linux can produce higher throughput compared to Xenomai, but it can be seen that RT systems almost did not affect the speed of static images recognition systems almost did not affect the speed of image recognition.
Date of Conference: 05-07 June 2019
Date Added to IEEE Xplore: 25 July 2019
ISBN Information:
Conference Location: Leeds, UK

I. Introduction

Single-board computers are gaining increasing popularity due to their size, with the result that they are widely used in robotics. But for the short form factor, you have to pay weak technical characteristics. Vision-based navigation is one of the crucial tasks that robotics address. Many factors are imposing practical limitations on a robot’s ability to see, learn and explore the environment. For this reason, navigation in unknown or partially unknown environments remains one of the biggest challenges in today's autonomous mobile robots implemented on single board computers [1]. This task requires a sufficiently large number of capacities, and to solve it in a single-board computer we should use all possible potential. To date, there are various ways of improving computer performance for a particular task. One of the possible solutions is to utilize of real-time (RT) systems, where compliance with specific time limits is very important, but, along with this, the overall system performance may decrease. Thus, the developer is faced with the hard choices of using real-time systems to dealing with performance or accuracy in image recognition and vision-based navigation. Objectives of this research are to study and use a real-time operating system (RTOS), Linux and their patches on a Raspberry Pi single board computer and to perform its further implementation in a small autonomous mobile robot equipped with the camera module and IR sensor.

References

References is not available for this document.