Novel landmark based navigation for autonomous mobile robot

Nobuya Okada, Daichi Abe, Satoshi Suzuki, Kojiro Iizuka, Takashi Kawamura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this study, we aim to achieve an autonomous locomotion of the mobile robot in the unknown environment regardless of indoor and outdoor. An information obtained from indoor and outdoor environment are completely different. In indoor case, dense information like a wall could be obtained. However, only sparse information is obtained in outdoor case. Therefore, in this study, dense information of indoor environment is convert to sparse information and same navigation algorithm is performed in the indoor and outdoor environment. For the first step of the study, the autonomous locomotion of the mobile robot in unknown indoor environment is realized. In particular, a novel landmark construction and detection method are proposed. The landmark is generated by combined image and shape features. By combining these features, some fault of each features are filled up and robust landmark detection in various environment could be achieved. In the landmark detection step, we represent the new matching method with automatic weighting for each features. The confidences are made from image and shape indicators of degree of the characteristic. The effectiveness of the proposed landmark is verified by experiment. Moreover, we introduce the novel landmark based graph SLAM. In our method, the landmark detection is performed on each node of pose graph. Then, if the robot find the landmark which is detected once, local loop closure is generated and optimization is performed. The main advantage of the method is that we can perform graph optimization before find global loop-closure. Hence, our method can minimize global error of the graph even if the robot don't come back the place visited at once. The effectiveness of the proposed graph SLAM is verified by numerical simulation and experiment.

Original languageEnglish
Title of host publicationMOVIC 2014 - 12th International Conference on Motion and Vibration Control
PublisherJapan Society of Mechanical Engineers
Publication statusPublished - 2014
Externally publishedYes
Event12th International Conference on Motion and Vibration Control, MOVIC 2014 - Sapporo, Hokkaido, Japan
Duration: 2014 Aug 32014 Aug 7

Other

Other12th International Conference on Motion and Vibration Control, MOVIC 2014
CountryJapan
CitySapporo, Hokkaido
Period14/8/314/8/7

Fingerprint

Mobile robots
Navigation
Robots
Experiments
Computer simulation

Keywords

  • Graph SLAM
  • Landmark construction
  • RGB-D camera
  • Shape features
  • Visual features

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Okada, N., Abe, D., Suzuki, S., Iizuka, K., & Kawamura, T. (2014). Novel landmark based navigation for autonomous mobile robot. In MOVIC 2014 - 12th International Conference on Motion and Vibration Control Japan Society of Mechanical Engineers.

Novel landmark based navigation for autonomous mobile robot. / Okada, Nobuya; Abe, Daichi; Suzuki, Satoshi; Iizuka, Kojiro; Kawamura, Takashi.

MOVIC 2014 - 12th International Conference on Motion and Vibration Control. Japan Society of Mechanical Engineers, 2014.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Okada, N, Abe, D, Suzuki, S, Iizuka, K & Kawamura, T 2014, Novel landmark based navigation for autonomous mobile robot. in MOVIC 2014 - 12th International Conference on Motion and Vibration Control. Japan Society of Mechanical Engineers, 12th International Conference on Motion and Vibration Control, MOVIC 2014, Sapporo, Hokkaido, Japan, 14/8/3.
Okada N, Abe D, Suzuki S, Iizuka K, Kawamura T. Novel landmark based navigation for autonomous mobile robot. In MOVIC 2014 - 12th International Conference on Motion and Vibration Control. Japan Society of Mechanical Engineers. 2014
Okada, Nobuya ; Abe, Daichi ; Suzuki, Satoshi ; Iizuka, Kojiro ; Kawamura, Takashi. / Novel landmark based navigation for autonomous mobile robot. MOVIC 2014 - 12th International Conference on Motion and Vibration Control. Japan Society of Mechanical Engineers, 2014.
@inproceedings{8eb20268bd8545db9a4f0ed9922ecfee,
title = "Novel landmark based navigation for autonomous mobile robot",
abstract = "In this study, we aim to achieve an autonomous locomotion of the mobile robot in the unknown environment regardless of indoor and outdoor. An information obtained from indoor and outdoor environment are completely different. In indoor case, dense information like a wall could be obtained. However, only sparse information is obtained in outdoor case. Therefore, in this study, dense information of indoor environment is convert to sparse information and same navigation algorithm is performed in the indoor and outdoor environment. For the first step of the study, the autonomous locomotion of the mobile robot in unknown indoor environment is realized. In particular, a novel landmark construction and detection method are proposed. The landmark is generated by combined image and shape features. By combining these features, some fault of each features are filled up and robust landmark detection in various environment could be achieved. In the landmark detection step, we represent the new matching method with automatic weighting for each features. The confidences are made from image and shape indicators of degree of the characteristic. The effectiveness of the proposed landmark is verified by experiment. Moreover, we introduce the novel landmark based graph SLAM. In our method, the landmark detection is performed on each node of pose graph. Then, if the robot find the landmark which is detected once, local loop closure is generated and optimization is performed. The main advantage of the method is that we can perform graph optimization before find global loop-closure. Hence, our method can minimize global error of the graph even if the robot don't come back the place visited at once. The effectiveness of the proposed graph SLAM is verified by numerical simulation and experiment.",
keywords = "Graph SLAM, Landmark construction, RGB-D camera, Shape features, Visual features",
author = "Nobuya Okada and Daichi Abe and Satoshi Suzuki and Kojiro Iizuka and Takashi Kawamura",
year = "2014",
language = "English",
booktitle = "MOVIC 2014 - 12th International Conference on Motion and Vibration Control",
publisher = "Japan Society of Mechanical Engineers",
address = "Japan",

}

TY - GEN

T1 - Novel landmark based navigation for autonomous mobile robot

AU - Okada, Nobuya

AU - Abe, Daichi

AU - Suzuki, Satoshi

AU - Iizuka, Kojiro

AU - Kawamura, Takashi

PY - 2014

Y1 - 2014

N2 - In this study, we aim to achieve an autonomous locomotion of the mobile robot in the unknown environment regardless of indoor and outdoor. An information obtained from indoor and outdoor environment are completely different. In indoor case, dense information like a wall could be obtained. However, only sparse information is obtained in outdoor case. Therefore, in this study, dense information of indoor environment is convert to sparse information and same navigation algorithm is performed in the indoor and outdoor environment. For the first step of the study, the autonomous locomotion of the mobile robot in unknown indoor environment is realized. In particular, a novel landmark construction and detection method are proposed. The landmark is generated by combined image and shape features. By combining these features, some fault of each features are filled up and robust landmark detection in various environment could be achieved. In the landmark detection step, we represent the new matching method with automatic weighting for each features. The confidences are made from image and shape indicators of degree of the characteristic. The effectiveness of the proposed landmark is verified by experiment. Moreover, we introduce the novel landmark based graph SLAM. In our method, the landmark detection is performed on each node of pose graph. Then, if the robot find the landmark which is detected once, local loop closure is generated and optimization is performed. The main advantage of the method is that we can perform graph optimization before find global loop-closure. Hence, our method can minimize global error of the graph even if the robot don't come back the place visited at once. The effectiveness of the proposed graph SLAM is verified by numerical simulation and experiment.

AB - In this study, we aim to achieve an autonomous locomotion of the mobile robot in the unknown environment regardless of indoor and outdoor. An information obtained from indoor and outdoor environment are completely different. In indoor case, dense information like a wall could be obtained. However, only sparse information is obtained in outdoor case. Therefore, in this study, dense information of indoor environment is convert to sparse information and same navigation algorithm is performed in the indoor and outdoor environment. For the first step of the study, the autonomous locomotion of the mobile robot in unknown indoor environment is realized. In particular, a novel landmark construction and detection method are proposed. The landmark is generated by combined image and shape features. By combining these features, some fault of each features are filled up and robust landmark detection in various environment could be achieved. In the landmark detection step, we represent the new matching method with automatic weighting for each features. The confidences are made from image and shape indicators of degree of the characteristic. The effectiveness of the proposed landmark is verified by experiment. Moreover, we introduce the novel landmark based graph SLAM. In our method, the landmark detection is performed on each node of pose graph. Then, if the robot find the landmark which is detected once, local loop closure is generated and optimization is performed. The main advantage of the method is that we can perform graph optimization before find global loop-closure. Hence, our method can minimize global error of the graph even if the robot don't come back the place visited at once. The effectiveness of the proposed graph SLAM is verified by numerical simulation and experiment.

KW - Graph SLAM

KW - Landmark construction

KW - RGB-D camera

KW - Shape features

KW - Visual features

UR - http://www.scopus.com/inward/record.url?scp=84925372652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925372652&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84925372652

BT - MOVIC 2014 - 12th International Conference on Motion and Vibration Control

PB - Japan Society of Mechanical Engineers

ER -