Unsupervised place recognition for assistive mobile robots based on local feature descriptions

Karasfi, Babak; Tang, Sai Hong; Samsudin, Khairulmizam; Ramli, Abdul Rahman; Jalalian, Afsaneh; Motlagh, Omid

doi:10.1177/0959651811406641

Cited by 3 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar approach using speeded-up robust features for clustering was reported. 59 The blob method provided high congruence and consistent correlation in detecting key points in divergent pairs. The blob method is a differential method based on derivatives of a function with respect to position.…”

Section: Trinocular Sensingmentioning

confidence: 97%

Divergent trinocular vision observers design for extended Kalman filter robot state estimation

Martínez‐García

Rivero-Juárez

Torres-Méndez

et al. 2018

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

Here, we report the design of two deterministic observers that exploit the capabilities of a home-made divergent trinocular visual sensor to sense depth data. The three-dimensional key points that the observers can measure are triangulated for visual odometry and estimated by an extended Kalman filter. This work deals with a four-wheel-drive mobile robot with four passive suspensions. The direct and inverse kinematic solutions are deduced and used for the updating and prediction models of the extended Kalman filter as feedback for the robot’s position controller. The state-estimation visual odometry results were compared with the robot’s dead-reckoning kinematics, and both are combined as a recursive position controller. One observer model design is based on the analytical geometric multi-view approach. The other observer model has fundamentals on multi-view lateral optical flow, which was reformulated as nonspatial–temporal and is modeled by an exponential function. This work presents the analytical deductions of the models and formulations. Experimental validation deals with five main aspects: multi-view correction, a geometric observer for range measurement, an optical flow observer for range measurement, dead-reckoning and visual odometry. Furthermore, comparison of positioning includes a four-wheel odometer, deterministic visual observers and the observer–extended Kalman filter, compared with a vision-based global reference localization system.

show abstract

Section: Trinocular Sensingmentioning

confidence: 97%

Divergent trinocular vision observers design for extended Kalman filter robot state estimation

Martínez‐García

Rivero-Juárez

Torres-Méndez

et al. 2018

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

show abstract

“…In our work, we used the Split and Merge method of line segment extraction using laser data which is largely used for extraction line based–feature process. 37–39…”

Section: Ugv System Modelmentioning

confidence: 99%

Simultaneous localization and mapping navigation of unmanned ground vehicle based on second-order smooth variable structure filter with improved technique to combat fading for advanced wireless communications

Mosbah

Demim

Mansoul

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

Simultaneous localization and mapping is very essential for autonomous navigation when the mobile robot is navigating in unknown environment without a global positioning system. Various techniques to solve the simultaneous localization and mapping problem have been extensively studied using the combination of low-cost sensors. Most of the work in mobile robotics still consists of finding solutions to problems in data exchange between mobile robot and communication control station, which is a challenging task. In fact, communication systems impose severe constraints in terms of channel capacity and transmission quality, because the transmission channel in communication systems is undergoing at the different physical phenomena like scattering, diffusion and diffraction, which occur interference and multiple path effects in wireless communications, while keeping these effects levels low. This article describes a simultaneous localization and mapping problem based on second-order smooth variable structure filter embedded in mobile robot equipped with a sensor for data wireless collection. The inclusion of the control in environments outside the mobile robot field of view can make the wireless communication simultaneous localization and mapping process much more difficult to find a solution under realistic conditions. In order to solve the simultaneous localization and mapping issue and to mitigate the fading phenomena, which affect the quality of service in advanced wireless communication systems, we use a new approach to combat the fading effect without requiring any statistical knowledge of the propagation channel parameters. Several experiments have been done in real-world applications, and good performances were obtained using a second-order smooth variable structure filter–simultaneous localization and mapping algorithm–based wireless communication.

show abstract

Unsupervised and Online Place Recognition for Mobile Robot based on Local Features Description

Tang¹,

Hamami²,

Karasfi³

et al. 2013

JOACE

View full text Add to dashboard Cite

Place recognition approaches have been used for solving topological mapping and localization problems. These approaches are usually performed in supervised and offline mode. In this paper, a robust appearance-based unsupervised and online place recognition algorithm, which is inspired from online sequential clustering methods, is introduced. This method combines several image features using Speedup Robust Features (SURF) by accumulating them into a union form of features inside each place cluster. In this method, the mobile robot captures omnidirectional visual information and converts them into topological place clusters. Experimental results show the robustness, accuracy, and efficiency of the method as well as its ability to create topological place clusters for solving mapping and qualitative localization problems. The performance of the developed system is remarkable in term of recognition precision performance.

show abstract

Unsupervised place recognition for assistive mobile robots based on local feature descriptions

Cited by 3 publications

References 36 publications

Divergent trinocular vision observers design for extended Kalman filter robot state estimation

Divergent trinocular vision observers design for extended Kalman filter robot state estimation

Simultaneous localization and mapping navigation of unmanned ground vehicle based on second-order smooth variable structure filter with improved technique to combat fading for advanced wireless communications

Unsupervised and Online Place Recognition for Mobile Robot based on Local Features Description

Contact Info

Product

Resources

About