Enhanced PCA-Based Localization Using Depth Maps with Missing Data

Carreira, Fernando; Calado, João Manuel Ferreira; Cardeira, Carlos; Oliveira, Paulo

doi:10.1007/s10846-013-0013-6

Cited by 13 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1). This self-localization system implements the PCA algorithm in depth images acquired from the ceiling to estimate the robot position (see [8] for more details). Such system requires the environment previous mapping, placing the robot in specific positions along a grid, covering all free space, to capture a set of ceiling depth images.…”

Section: Navigation System Architecturementioning

confidence: 99%

“…The PCA algorithm was proposed by [6] as the positioning system in a terrain reference navigation of underwater vehicles. [7] and [8] implemented a PCA-based self-localization system for mobile robots, using ceiling images, that provides globally stable estimates, from Kalman filters (KF), but the proposed approach was not integrated into a closed loop control system to perform navigation tasks. The use of depth images in [8] improves the system robustness to cope with varying illumination conditions.…”

Section: Introductionmentioning

confidence: 99%

“…With this system, no specific features extraction and model linearizations are required. To achieve this, the presented work combines the PCA-based self-localization system from ceiling depth images [8] with a motion controller, based on the dipolar navigation function (DNF) [13], [15], to drive the robot along a set of waypoints extracted from a GVD. Such roadmap is built according to the free space environment, using the ceiling mapping information and implementing the approach proposed by [11].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Navigation System for Mobile Robots Using PCA-Based Localization from Ceiling Depth Images: Experimental Validation

Carreira

Calado

Cardeira³

et al. 2018

2018 13th APCA International Conference on Control and Soft Computing (CONTROLO)

Self Cite

View full text Add to dashboard Cite

This paper aims the experimental validation of a mobile robot navigation system, using self-localization based on principal component analysis (PCA) of ceiling depth images. In this approach, a roadmap based on generalized Voronoi diagram (GVD) is built from an occupancy grid, that is defined in the ceiling mapping to the PCA database. The system resorts to the Dijkstra algorithm to planning paths, using the GVD-based roadmap, from which a set of waypoints are extracted. During the mission, the robot is commanded by a controller based on dipolar navigation functions (DNF) along the waypoints, being self-located using only the information provided from ceiling depth images and other on-board sensors. The navigation system ensures that the robot reaches its destination, travelling along safety trajectories, while computing its pose with global stable estimates, from Kalman filters (KF). The navigation is achieved without the need to structure the environment, searching by specific features, and to linearize the model. The results are experimentally validated in an indoor environment, using a differential-drive mobile robot.

show abstract

Section: Navigation System Architecturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Navigation System for Mobile Robots Using PCA-Based Localization from Ceiling Depth Images: Experimental Validation

Carreira

Calado

Cardeira³

et al. 2018

2018 13th APCA International Conference on Control and Soft Computing (CONTROLO)

Self Cite

View full text Add to dashboard Cite

show abstract

“…made studies in warehouse environments using visual odometry of ceiling images [6], Markov Localization [7] and a 3D camera applied to a depth map of the ceiling. Carreira et al [8] also use depth maps and introduce a technique to deal with missing data from the 3D camera. Both S. Kim & C. Park [9], C. Huang et al [10] and [11] present some interesting studies based on localization with ceiling images.…”

Section: Introductionmentioning

confidence: 99%

“…Particle Filter based approaches [12] are multi-model but their performance is strongly related to the amount of particles and re-sampling techniques used. The approach shown in [8] is based on an LPV (Linear Parameter Varying) robot model that avoids linearization, proving globally asymptotic dynamics. However it is unimodal and requires a map of the environment.…”

Section: Introductionmentioning

confidence: 99%

Mobile Robot Localisation for Indoor Environments Based on Ceiling Pattern Recognition

Dias

Schäfer

Natal

et al. 2015

2015 IEEE International Conference on Autonomous Robot Systems and Competitions

Self Cite

View full text Add to dashboard Cite

In this paper a multi-modal localisation system, that estimates a robot position in indoor environments using only on-board sensors, namely a webcam and a compass, is presented. Ceiling lights are used as beacons. Their position is previously known or self-learned during normal operation. Markov Localisation (ML) is both simulated and experimentally validated. For the prediction step it combines IMU (Inertial Measurement Unit) data and image parameters to compute the attitude of the robot. The update step is then calculated by measuring the distance to possibly visible ceiling lights. The experimental validation of the proposed solution shows that the robot position estimate converges to its real position and the error is kept within decimetres of magnitude.

show abstract

An Innovative Monocular Mobile Object Self-localization Approach Based on Ceiling Vision

Cuzzocrea

Camilotti

Mumolo

2021

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

This study deals with the estimation of the position of a mobile object using ceiling landmarks images acquired by a low resolution camera placed on a mobile object. The mobile object is moving in an indoor environment where light is given by electric lamps with circular holders. The images of the circular holders are projected on the image plane of the camera and are processed by means of computer vision algorithms. The pixels of the images of the light holders on the ceiling are mapped to the pixels of the images of the light holders on the image plane of the camera by means of a two dimensional dynamic programming algorithm (2D-DPA). The projection distortions are thus compensated and this reduces the estimation errors. The algorithm described in this paper estimates the distance from the camera lens to the center of the landmarks using only ceiling vision. Localization can be easily obtain from such distance estimations. The projections are geometrically described and the distance estimation is based on the pixels mapping information obtained by 2D-DPA.

show abstract

Enhanced PCA-Based Localization Using Depth Maps with Missing Data

Cited by 13 publications

References 22 publications

Navigation System for Mobile Robots Using PCA-Based Localization from Ceiling Depth Images: Experimental Validation

Navigation System for Mobile Robots Using PCA-Based Localization from Ceiling Depth Images: Experimental Validation

Mobile Robot Localisation for Indoor Environments Based on Ceiling Pattern Recognition

An Innovative Monocular Mobile Object Self-localization Approach Based on Ceiling Vision

Contact Info

Product

Resources

About