Efficient Autonomous Navigation Algorithm Based on Windows 10 IoT Core and Low-cost Hardware for Mobile Robots :Windows 10 IoT Core와 저비용 하드웨어 기반의 모바일 로봇용 효율적인 자율 내비게이션 알고리즘

Onesphore Ingabire

추천

검색

자료유형: 학위논문

저자정보: Onesphore Ingabire (동의대학교, 동의대학교 대학원)

지도교수: 장종욱

발행연도: 2020

저작권: 동의대학교 논문은 저작권에 의해 보호받습니다.

이용수4

이 논문의 연구 히스토리 (2)

2021

Implementation of an Autonomous Navigation algorithm for TurtleBot 2 based Windows 10 IoT Core and Low-cost Hardware

Onespho , e Ingabi , e 외 3명 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING 2021.02 학술대회자료

2020

Efficient Autonomous Navigation Algorithm Based on Windows 10 IoT Core and Low-cost Hardware for Mobile Robots

Onespho , e Ingabi , e 컴퓨터공학과 2020.01 학위논문

이 논문의 후속연구가 궁금하신가요?
연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
이 논문의 연구 히스토리 확인하기

초록· 키워드

오류제보하기

로봇 공학 분야가 점점 더 널리 보급됨에 따라 로봇이 데이터를 처리하고 보다 정확하고 정확하며 효과적으로 작업을 수행할 수 있도록 하는 새로운 기술의 개발에 대한 요구가 높아지고 있다. 지금까지 모바일 로봇이 실내 또는 실외 환경에서 탐색할 수 있도록 서로 다른 알고리즘을 사용하는 여러 연구가 수행되었다. 자율 내비게이션 알고리즘을 구축하는 데 가장 많이 사용되는 프레임워크 중 하나는 로봇 애플리케이션 개발에 널리 사용되는 오픈소스 로봇 운영 체제인 ROS(Robot Operating System)가 있다. ROS 프레임워크를 사용하여 알려진 환경과 알려지지 않은 환경 모두를 탐색하는 방법을 TurtleBot 2에서 부분적 실행 성공이 확인되었다. 그러나 연구자들은 구현에 관련된 비용과 많은 하드웨어 자원 소비 (ROS 라이브러리로 인해)로 인해 몇 가지 제한 사항을 지적해 왔다. 저렴한 하드웨어를 사용하는 솔루션이 제안되었지만 저렴한 장치에서 본격적인 ROS를 실행하면 시스템 성능에 여전히 큰 영향을 미친다.
저비용 장치의 등장과 소형 장치를 위한 새로운 소형 운영 체제의 도입으로 다양한 개선 사항이 모바일 로봇을 위한 새로운 아키텍처의 설계뿐만 아니라 경량 운영 체제를 기반으로 하는 로봇 소프트웨어의 구현에도 영향을 주었다. 본 논문에서는 저가형 임베디드 장치(예 : Raspberry Pi)에서 실행되는 TurtleBot 2 용 Windows 10 IoT 코어 기반 자율 내비게이션 알고리즘에 대한 연구를 소개한다. 먼저, Raspberry pi에서 실행되는 Windows 10 IoT 코어를 기반으로 새로운 아키텍처를 설계했다. 둘째, UWP (Universal Windows Platform) 프레임워크 및 C# 프로그래밍 언어를 사용하여 TurtleBot 2를 제어하기 위한 효과적인 자율 탐색 알고리즘을 구현했다. 마지막으로 데스크톱에서 실행되는 ROS 프레임워크에 구축된 알고리즘의 성능과 비교하여 본 논문에서 제안된 알고리즘과 성능을 비교하였다. 결과는 동일한 환경에서 ROS 프레임워크 접근 방식에 비해 빠른 응답성과 우수한 에너지 소비(배터리 사용량 절감)패턴을 본 논문에서 제안된 알고리즘에서 증명하였다.

As the field of robotics becomes more and more prevalent, so does the requirement to develop new technologies that enable the robot to process data and perform tasks more precisely, accurately, and effectively. So far, several studies using different algorithms have been conducted in order to allow mobile robots to navigate in an indoor or outdoor environment. One of the most popular frameworks used to build an autonomous navigation algorithm is the Robot Operating System (ROS), an open source widely used to develop robot applications. Using the ROS framework, some success has been identified with TurtleBot 2,
navigating in both known and unknown environments. However, researchers have pointed out some limitations due to both the cost involved in the implementation and to the high consumption of resources
(due to the ROS libraries). Although solutions have been proposed, such us using low-cost hardware, running the full-fledged ROS on low-cost devices still has a tremendous impact on the performance of the system.
With the emerging of low-cost devices and introductions of new compact operating systems made for smaller devices, various enhancements have not only impacted the design of the new architecture for mobile robots but also the implementations of the robot’s software based on lightweight operating systems. In this paper, I present a study on a Windows 10 IoT core based autonomous navigation algorithm for TurtleBot 2 running on a low-cost device (such as Raspberry pi). Firstly, I designed new architecture based on Windows 10 IoT core running on Raspberry pi. Secondly, I implemented an effective autonomous navigation algorithm for controlling TurtleBot 2 using the Universal Windows Platform (UWP) framework and C# programming language. And finally, I evaluated the performance of the proposed algorithm in comparison with the performance of the algorithm built on
the ROS framework running on a desktop. The results have shown fast responsiveness, good consumption of energy and affordable cost of the proposed algorithm compared to the ROS framework approach.

1. Introduction ············································································································· 1
1.1. Motivation ········································································································ 1
1.2 Scope of this paper ························································································ 3
1.3 Methodology of the study ············································································ 4
1.4 Organization of the paper ············································································· 5
2. Background and related work ············································································ 6
2.1. Existing related research ············································································· 6
2.2. Overview of ROS (Robot Operating System) ······································ 9
2.3. Windows 10 IoT core ················································································· 10
2.3.1. Introduction ····························································································· 10
2.3.2. Overview ······························································································· 11
2.3.3. The Motivation for choosing Windows 10 IoT core ·················· 12
2.3.3.1 Windows 10 IoT core capabilities ·················································· 12
2.3.3.2 Windows 10 IoT core with hardware ··········································· 13
2.3.3.3 Windows 10 IoT core and video support ···································· 13
2.3.3.4 Windows 10 IoT core support many screens ····························· 14
2.4. Universal Windows Platform app (UWP app) ····································· 14
2.4.1 The power of UWP for devices ························································ 15
2.5. The protocol of TurtleBot 2 (KOBUKI) ················································ 16
2.5.1. Understanding Kobuki protocol ······················································· 16
2.5.2. Command packets ················································································· 18
3. Autonomous Navigation Algorithm Based on Windows 10 IoT Core
and Low-cost Hardware for TurtleBot 2 ························································· 20
3.1. Description of the system architecture of the for TurtleBot 2. ····· 20
3.1.1. Remote PC side description ····························································· 21
3.1.1.1 Remote PC hardware requirements ··············································· 21
3.1.1.2 Remote PC software requirements ················································· 22
3.1.2. Raspberry pi low-cost hardware description ······························ 22
3.1.2.1 Raspberry pi and Windows 10 IoT core ····································· 23
3.1.2.2 Raspberry pi with the TurtleBot 2 ················································ 23
3.1.3. Rplidar A2 sensor description ··························································· 25
3.1.4. TurtleBot 2 description ······································································· 26
3.1.4.1. TurtleBot 2 hardware ······································································· 27
3.1.4.2. TurtleBot 2 software ········································································ 28
3.2. Autonomous navigation ············································································ 28
3.2.1. Path planning algorithm ·································································· 29
3.2.2. Obstacle avoidance algorithm ···························································· 31
4. Implementation and results ··············································································· 33
4.1. Implementation of the proposed system. ··············································· 33
4.1.1. Creation of the map of the area of the experiment ··················· 34
4.1.2. Dijkstra''s algorithm implementation. ··············································· 36
4.1.3. Configuration of the devices connected to Raspberry pi ··········· 37
4.1.4. Implementation of the navigation controller ·································· 38
4.1.4.1. Path planning algorithm ··································································· 38
4.1.4.2. Obstacle Avoidance ··········································································· 40
4.1.5. Implementation of the User Interface ·············································· 41
4.2. Results and discussion. ·············································································· 42
4.2.1. Autonomous navigation based path planning results ················· 43
4.2.2. Autonomous navigation based obstacle avoidance. ··················· 45
4.2.3. User Interface based client-server architecture ··························· 46
4.3. Performance comparison between the proposed system and ROS app performance ······· 47
5. Conclusion ··········································································································· 50
References ·················································································································· 52

최근 본 자료

전체보기

구분	그룹	데이터 항목
AI 학습용 데이터	원문	원문 PDF 파일
AI 학습용 데이터	원문 + 메타 (기본/상세)	원문 PDF 파일 및 서지정보 CSV
대량 구매용 데이터	B2B 구독 방식	특정 자료 한정으로 원문 접근 권한 부여
대량 구매용 데이터	URL 전달 방식	바로 PDF 뷰어를 열람할 수 있는 URL 제공

구분	그룹	데이터 항목
AI 학습용 데이터	기본 메타	발행기관명, 간행물명, 권호명, 권(vol), 호(issue), 통권, 발행연도, 발행월, 논문명, 저자명, 시작페이지, 종료페이지, 전체페이지, 상세페이지URL
상세 메타 데이터	발행기관 메타	발행기관 이명, 영문명, 창립연도, 홈페이지URL, 발행기관 소개
	간행물 메타	부제목, 간행물 유형, ISSN, ISBN, 최초발행연도, 폐간연도, 간행빈도, 발행주기, 등재사항, 이용수, 피인용수, 권호수, 논문수, 표지이미지
	논문 메타	작성 언어, 부제목, 대등제목, 목차, 키워드, 초록, 이미지, 참고문헌, 이용수, 피인용수, 논문활용도, DBpia통합주제분류, KDC분류, DDC분류, 한국연구재단분류, UCI, DOI
	저자 메타	소속기관, 소속부서, 직급, 연구분야, 연구키워드, 이용수, 피인용수, 저자 논문활용도

구분	그룹	데이터 항목
※ 결합형/맞춤형 메타 데이터는 신청 내용에 따라 다양하게 제공 가능
이용순위 정보	주제분야별 많이 이용된 논문	“인문학”에서 많이 이용된 논문 TOP100
	이용기관별 많이 이용된 논문	“중고등학교”에서 많이 이용된 논문 TOP100
	세부기관별 많이 이용된 논문	“서울대학교”에서 많이 이용된 논문 TOP100
	키워드별 많이 이용된 논문	“Chat GPT”에서 많이 이용된 논문 TOP100
키워드 정보	많이 이용된 키워드	특정기간/분야/저널 내 많이 이용된 키워드
	많이 발행된 키워드	특정기간/분야/저널 내 많이 발행된 키워드
	많이 검색된 키워드	특정기간/분야/저널 내 많이 검색된 키워드
	연구 트렌드 키워드	특정 키워드 연관 연구동향 분석 데이터 키워드

논문 기본 정보

이 논문의 연구 히스토리 (2)

초록· 키워드

목차

최근 본 자료

댓글(0)