Development of an EKF-based localization algorithm using compass sensor and LRF

Hoang, T. T.; Duong, P. M.; Van, Nguyen Thị Thanh; Viet, D. A.; Vinh, Trần Quang

doi:10.1109/icarcv.2012.6485182

Cited by 11 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The operation environment is flat-floor constructed by cement with several wooden plates surrounded ( Figure Figure The RMSE of estimations in Y direction in orientation 16). Details of the robot system can be referred from our previous work [15]. The initial value of matrices Q Q Q and R R R is similar to the second simulation case.…”

Section: Experiments a Experiments Setupmentioning

confidence: 99%

See 1 more Smart Citation

Mobile robot localization using fuzzy neural network based extended kalman filter

Nguyen

Phung

Tran

et al. 2013

JCC

View full text Add to dashboard Cite

Tóm tắt. Báo cáo đề xuất cải tiến chất lượng của bộ lọc Kalman mở rộng cho bài toán định vị cho robot di động. Một hệ logic mờ được sử dụng để hiệu chỉnh theo thời gian thực các ma trận hiệp phương sai của bộ lọc. Tiếp đó, một mạng nơron được cài đặt để hiệu chỉnh các hàm thành viên của luật mờ. Mục đính là để tăng độ chính xác và tránh sự phân kỳ của bộ lọc Kalman khi các ma trận hiệp phương sai được chọn cố định hoặc chọn sai. Chương trình mô phỏng và các thực nghiệm trên robot thực tại phòng thí nghiệm được thực hiện để đánh giá hiệu quả của thuật toán. Kết quả cho thấy bộ lọc đề xuất cho hiệu quả tốt hơn bộ lọc Kalman mở rộng trong vấn đề định vị cho robot di động.Từ khóa. Logic mờ, mạng nơron, bộ lọc kalman mở rộng, định vị, robot di động.Abstract. This paper proposes an approach to improve the performance of the extended Kalman filter (EKF) for the problem of mobile robot localization. A fuzzy logic system is employed to continuously adjust the noise covariance matrices of the filter. A neural network is implemented to regulate the membership functions of the antecedent and consequent parts of the fuzzy rules. The aim is to gain the accuracy and avoid the divergence of the EKF when the noise covariance matrices are fixed or incorrectly determined. Simulations and experiments are given. The results show that the proposed filter is better than the EKF in localizing the mobile robot.

show abstract

Section: Experiments a Experiments Setupmentioning

confidence: 99%

“…In each evaluation, a Monte Carlo simulation with 100 times is executed to compare the performance of the EKF and the FNN-EKF. Parameters for simulations are extracted from a real mobile robot built by the author's research group at the university's laboratory [15].…”

Section: Simulations a Simulation Setupmentioning

confidence: 99%

Mobile robot localization using fuzzy neural network based extended kalman filter

Nguyen

Phung

Tran

et al. 2013

JCC

View full text Add to dashboard Cite

show abstract

“…Scan matching using laser range finders (LRF) to measure the distance to walls is one method of self-localization [1][2][3][4][5][6][7]. However, this method cannot be used for self-positioning when there is no unevenness due to corners or columns in the wall form, because optimal matching becomes impossible.…”

Section: Introductionmentioning

confidence: 99%

Improving landmark detection accuracy for self-localization through baseboard recognition

Premachandra

Murakami

Gohara

et al. 2016

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Acquiring information related to the surrounding environment and environmental mapping are important issues for realizing autonomous robot movement in an unknown environment, and these processes require position estimations for self-localization. We have conducted previous research related to self-localization in indoor environments through baseboard recognition. In that method, a mobile robot performs self-localization using camera-acquired images, from which the intersection of baseboards and the vertical lines of attached doorframes are registered as landmarks. However, this method is limited in that self-localization cannot be performed in cases where baseboards are not partially available or where walls and baseboards are the same color. The present research aims at addressing these issues and implementing the method in an actual mobile robot. The implementing robot is allowed to move autonomously, performing mapping and self-localization in real time. Addressing the problem of same-colored walls requires identification of the border between the wall and the baseboard, so we propose an image processing method for identifying these lines. The problem of lack of baseboards is solved through supplemental use of odometry, which does not rely on visual characteristics. The proposed method is experimentally verified through use of our algorithm to recognize baseboards, perform self-localization, and create maps. The results verify that baseboards can be recognized even when they are the same color as walls. We furthermore verify that landmark-mapping performance when moving in hallways is improved over the previous version.

show abstract

“…The laser range finder and sonar sensors in association with other sensors attached in a mobile robot. [14][15].…”

Section: Introductionmentioning

confidence: 99%

Proposal of algorithms for navigation and obstacles avoidance of autonomous mobile robot

Hoang¹,

Hiep²,

Duong³

et al. 2013

2013 IEEE 8th Conference on Industrial Electronics and Applications (ICIEA)

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents algorithms to navigate and avoid obstacles for an in-door autonomous mobile robot. A laser range finder is used to obtain 3D images of the environment. A new algorithm, namely 3D-to-2D image pressure and barriers detection (IPaBD), is proposed to create a 2D global map from the 3D images. This map is basic to design the trajectory. A tracking controller is developed to control the robot to follow the trajectory. The obstacle avoidance is addressed with the use of sonar sensors. An improved vector field histogram (Improved-VFH) algorithm is presented with improvements to overcome some limitations of the original VFH. Experiments have been conducted and the result is encouraged.

show abstract

Development of an EKF-based localization algorithm using compass sensor and LRF

Cited by 11 publications

References 11 publications

Mobile robot localization using fuzzy neural network based extended kalman filter

Mobile robot localization using fuzzy neural network based extended kalman filter

Improving landmark detection accuracy for self-localization through baseboard recognition

Proposal of algorithms for navigation and obstacles avoidance of autonomous mobile robot

Contact Info

Product

Resources

About