In this paper, we focus on some perceptual functions required by a
generic task “GOTO” in natural environments; in previous
works, only geometrical modeling has been used to deal with two
fundamental tasks: landmark extraction and recognition for sensor-based
motion control or robot localization, and terrain modeling for motion
planning. Geometrical representations alone lead to a bulky model, and,
after some iterations, to a combinatorial explosion. We present here,
higher level representations; from a range image, given some assumptions
on the perceived scene (even ground with few objects), we propose a
segmentation algorithm to extract simple semantical representations for
the ground and the objects; then, we can analyze the relative positions
of the objects to build a topological scene description. Both models
constitute the scene model, needed for further incremental environment
"Thrun  builds a topological graph based on an occupancy grid. Betgé-Brezetz et al.  describe, in a topological way, the locations starting with the geometrical information. The authors build planes to represent the flat and superquadrics for the obstacles representation. "
[Show abstract][Hide abstract] ABSTRACT: In this paper, a new methodology to build compact local maps in real time for outdoor robot navigation is presented. The environment information is obtained from a 3-D scanner laser. The navigation model, which is called traversable region model, is based on a Voronoi diagram technique, but adapted to large outdoor environments. The model obtained with this methodology allows a definition of safe trajectories that depend on the robot's capabilities and the terrain properties, and it will represent, in a topogeometric way, the environment as local and global maps. The application presented is validated in real outdoor environments with the robot called GOLIAT. 16 pages, 46 figures. This work was supported by the Spanish Government through the MICYT project DPI2003-01170.
IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans 02/2008; 38(1). DOI:10.1109/TSMCA.2007.904786 · 2.18 Impact Factor
"Some other works tackle the contour extraction problem by analyzing the enclosed surfaces , ; therefore, contour and region are simultaneously extracted.  brought forward an adaptive approach that extracts closed contour by applying a process of hypotheses generation and verification. "
[Show abstract][Hide abstract] ABSTRACT: This paper presents an improvement over a pre- vious contour closure algorithm. Assuming that edge points are given as input, the proposed approach consists of two steps. Similarly than the previous approach, the minimum spanning tree of a partially connected graph is initially com- puted. Then, a morphological filter removes noisy links and finally open contours are closed by minimizing a linking cost function. Advantages of the proposed technique lie in the lack of user defined thresholds and non-dependency of edge point density. Experimental results with synthetic and real range images are presented showing encouraging results with uniform and non-uniform edge points' distribution. Human being can easily extract objects' contours after watching their defining set of points. Unfortunately, this simple and almost trivial action for the human being is a quite difficult task to be automatically performed. A lot of work has been carried out in the computer vision commu- nity, some of them using the psychology as an inspiration source. Human visual system can detect many patterns of image elements; the ability to extract significant image relations without any knowledge of the image content and group them to obtain meaningful higher-level structure is usually referred as perceptual grouping. Research in per- ceptual grouping was started in 1920's by Gestalt psychologists. The hierarchical grouping principles, pro- posed by Gestalt psychologists, embodied such concepts as grouping by proximity, similarity, continuation, clo- sure, and symmetry (1). Several techniques have been developed in the range image literature to compute closed contours. Classically, they were inspired from the 2D image processing field; hence, some of the proposed 3D contour closure approaches have been based on the use of morphological operators (e.g., (2), (3), (4)). Other approaches try to link edge points according to local measures of continuity and smoothness, with no a priori information about the object shape. These techniques include several well-know algo- rithms from different fields (deformable models,
Proceedings of the 2005 IEEE International Conference on Robotics and Automation, ICRA 2005, April 18-22, 2005, Barcelona, Spain; 01/2005
"For its simplicity and computing time, the approximation proposed by Betgé-Brezetz to obtain the normal vector − → N i in each three-dimensional point is chosen. This method is widely explained in . For the robot's physical constraints, two thresholds must be determined: the maximum slope ξ max and the minimum slope ξ min . "
[Show abstract][Hide abstract] ABSTRACT: One of the new challenges in robotics is the au-tonomous navigation in outdoor environments. To-days applications, like civil security, mining, scientific exploration and field service robotics, are increasing the interest in robots which are able to navigate in unstructured and changing environments, without hu-man supervision. A methodology for outdoor environ-ments modelling is presented in this paper. The re-sult will be a traversable regions model, based on the Voronoi Diagram technic, which is simple to use and to obtain. The model can be calculated in real-time and it is adapted not only to the environment's type, where the robot evolves, but also to the robot's phys-ical constraints. Experimental results carried out in a real outdoor environment, with an outdoor mobile robot, named GOLIAT , are presented.
11th International Conference on Advanced Robotics, ICAR 2003 ., Coimbra, Portugal.; 06/2003
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.