-
[show abstract]
[hide abstract]
ABSTRACT: In this paper a feature detection algorithm based on a new curve gradient model is proposed for simultaneous localization and mapping (SLAM) for complex outdoor environments. The curve gradient model is derived for data segmentation and has the advantage of being suitable for segmentation of data from various types of feature such as point feature and circular feature. The real time implementation of SLAM together with this feature extraction algorithm is realized by using a combination of odometry and laser scanner data. The system was tested on a long walk way at Nanyang Technological University. The experimental results show that the feature detection algorithm performs well during SLAM.
Control, Automation, Robotics and Vision Conference, 2004. ICARCV 2004 8th; 01/2005
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, two new algorithms for feature detection are presented. The first one can detect edge and circle features accurately using the Gaussian-Newton optimization method to fit the circle parameters. It consists of two parts: the first is the segmentation of data of each scan which is followed by parameter acquisition. The algorithm is off-line in nature as the segmentation and parameter acquisition are carried out after each scan data is collected. We also present another algorithm which is on-line and applies a multiple models filtering approach to handle features of different geometries such as lines and circles. It detects the circle features using the unscented Kalman filter. Experimental results show that the proposed two approaches are efficient in detecting features.
Control and Automation, 2003. ICCA '03. Proceedings. 4th International Conference on; 07/2003
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we present a new approach for natural feature extraction using a laser scanner for the purpose of localization in outdoor environments. In semi-structured outdoor environments, naturally predominant features such as trees and edges are considered. The proposed method applies a batch processing which carries out feature extraction after measurements from a full scan are received. The algorithm consists of data segmentation and parameter acquisition. A modified Gauss-Newton method is proposed for fitting circle parameters iteratively. The natural features extracted through this approach are more robust than those obtained by existing methods. In order to reduce the estimation error caused by the linearization in the extended Kalman filtering (EKF), a particle filter is applied to realize the prediction and validation by integrating data from both the laser range sensor and encoder in outdoor environments. The proposed feature extraction and localization algorithms are verified in a real world experiment.
Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 IEEE International Conference on;
-
[show abstract]
[hide abstract]
ABSTRACT: We present an efficient integer programming (IP) based data association approach to simultaneous localization and mapping (SLAM). In this approach, the feature based SLAM data association problem is formulated as a 0-1 IP problem. The IP problem is approached by first solving a relaxed linear programming (LP) problem. Based on the optimal LP solution, a suboptimal solution to the IP problem is then obtained by applying an iterative heuristic greedy rounding (IHGR) procedure. Unlike the traditional nearest-neighbor (NN) algorithm, the proposed algorithm deals with a global matching between existing features and measurements of each scan and is more robust for an environment of high density features which is usually the case in outdoor environments. We provide a simulation study where the NN algorithm fails whereas our proposed algorithm performs satisfactorily. Experimental results also demonstrate the effectiveness and efficiency of our approach.
Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 IEEE International Conference on;
