Mobile robot SLAM for line-based environment representation

Garulli, Andrea; Giannitrapani, Antonio; Rossi, Alessandro; Vicino, Antonio

doi:10.1109/cdc.2005.1582461

Cited by 91 publications

(100 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The common reliance on line extraction [9], [8], [10], [11], [12] indicates the importance of orientation in semantic mapping. However, we cannot readily reuse these results, due to clutter and discontinuities in the physical structures.…”

Section: Contributions and Approachmentioning

confidence: 99%

Sensor based adaptive metric-topological cell decomposition method for semantic annotation of structured environments

Shahbandi

Åstrand

Philippsen

2014

2014 13th International Conference on Control Automation Robotics &Amp; Vision (ICARCV)

View full text Add to dashboard Cite

Abstract-A fundamental ingredient for semantic labeling is a reliable method for determining and representing the relevant spatial features of an environment. We address this challenge for planar metric-topological maps based on occupancy grids. Our method detects arbitrary dominant orientations in the presence of significant clutter, fits corresponding line features with tunable resolution, and extracts topological information by polygonal cell decomposition. Real-world case studies taken from the target application domain (autonomous forklift trucks in warehouses) demonstrate the performance and robustness of our method, while results from a preliminary algorithm to extract corridors, and junctions, demonstrate its expressiveness. Contribution of this work starts with the formulation of metric-topological surveying of environment, and a generic n-direction planar representation accompanied with a general method for extracting it from occupancy map. The implementation also includes some semantic labels specific to warehouse like environments.

show abstract

Section: Contributions and Approachmentioning

confidence: 99%

Sensor based adaptive metric-topological cell decomposition method for semantic annotation of structured environments

Shahbandi

Åstrand

Philippsen

2014

2014 13th International Conference on Control Automation Robotics &Amp; Vision (ICARCV)

View full text Add to dashboard Cite

show abstract

“…As the robot navigates through the environment and new features are detected by the mobile robot's sensors, they are added into the SLAM system state and into its covariance matrix [1,4,7,42]. Thus, the dimension of both the SLAM system state and its covariance matrix is dynamic [2,23,47] and, if no feature is deleted from the SLAM algorithm, it is also incremental. Thus, the computational cost of the SLAM algorithm increases as the robot acquires more information from the environment [41,48].…”

Section: Second Approach: An Eif-slam Case Studymentioning

confidence: 99%

“…The nature of the feature uses is strictly dependent on the sensor capabilities. Thus, in [23] the authors use a line-based SLAM, where lines are extracted by a laser range sensor and the implementation of recursive algorithms to estimate lines within the Cartesian space; in [3], the author uses point-based features (like corners) to perform a SLAM algorithm. On the other hand, [24] uses a stereo-vision system to estimate the orientation of the camera while mapping the surrounding environment.…”

Section: Introductionmentioning

confidence: 99%

Covariance-Based Measurement Selection Criterion for Gaussian-Based Algorithms

Cheein

2013

Entropy

View full text Add to dashboard Cite

Abstract:Process modeling by means of Gaussian-based algorithms often suffers from redundant information which usually increases the estimation computational complexity without significantly improving the estimation performance. In this article, a non-arbitrary measurement selection criterion for Gaussian-based algorithms is proposed. The measurement selection criterion is based on the determination of the most significant measurement from both an estimation convergence perspective and the covariance matrix associated with the measurement. The selection criterion is independent from the nature of the measured variable. This criterion is used in conjunction with three Gaussian-based algorithms: the EIF (Extended Information Filter), the EKF (Extended Kalman Filter) and the UKF (Unscented Kalman Filter). Nevertheless, the measurement selection criterion shown herein can also be applied to other Gaussian-based algorithms. Although this work is focused on environment modeling, the results shown herein can be applied to other Gaussian-based algorithm implementations. Mathematical descriptions and implementation results that validate the proposal are also included in this work.

show abstract

“…Garulli et al [10] use EKF for mapping using linear features. They apply segmentation and line fitting steps to laser scanner data one after another continuously until a stopping condition is reached.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous localization and mapping with limited sensing using Extended Kalman Filter and Hough transform

Özışık

Yavuz

2016

Teh. vjesn.

View full text Add to dashboard Cite

Original scientific paper The problem of a robot to create a map of an unknown environment while correcting its own position based on the same map and sensor data is called Simultaneous Localization and Mapping problem. As the accuracy and precision of the sensors have an important role in this problem, most of the proposed systems include the usage of high cost laser range sensors, and relatively newer and cheaper RGB-D cameras. Laser range sensors are too expensive for some implementations, and RGB-D cameras bring high power, CPU or communication requirements to process data on-board or on a PC. In order to build a low-cost robot it is more appropriate to use low-cost sensors (like infrared and sonar). In this study it is aimed to create a map of an unknown environment using a low cost robot, Extended Kalman Filter and linear features like walls and furniture. A loop closing approach is also proposed here. Experiments are performed in Webots simulation environment. Keywords: Extended Kalman Filter; Hough transform; limited sensing; loop closing; SLAM Simultano lokaliziranje i kartiranje s ograničenom indikacijom odstupanja uz primjenu produljenog Kalman filtra i Hough transformacijeIzvorni znanstveni članak Problem robota da izradi kartu nepoznatog okruženja uz ispravljanje vlastitog položaja na temelju iste karte i podataka senzora naziva se problem simultanog lokaliziranja i kartiranja (mapiranja). Budući da je točnost i preciznost senzora od velike važnosti u rješavanju tog problema, većina predloženih sustava uključuje primjenu skupih laserskih senzora daljine te relativno novije i jeftinije RGB-D kamere. Laserski senzori daljine su preskupi za neke primjene, a RGB-D kamere imaju veliku snagu, CPU ili sve što je potrebno za obradu podataka direktno ili na PC-u. Za izradu jeftinog robota bolje je primijeniti senzore niske cijene (poput infracrvenih ili sonarnih). Cilj je ovoga rada izraditi kartu nepoznatog okruženja uz primjenu jeftinog robota, produljenog Kalman filtra i linearnih obilježja, kao što su zidovi i namještaj. Ovdje se također predlaže pristup zatvaranja petlje. Eksperimenti su provedeni u okruženju Webots simulacije.

show abstract

Mobile robot SLAM for line-based environment representation

Cited by 91 publications

References 12 publications

Sensor based adaptive metric-topological cell decomposition method for semantic annotation of structured environments

Sensor based adaptive metric-topological cell decomposition method for semantic annotation of structured environments

Covariance-Based Measurement Selection Criterion for Gaussian-Based Algorithms

Simultaneous localization and mapping with limited sensing using Extended Kalman Filter and Hough transform

Contact Info

Product

Resources

About