http://dl.gi.de/handle/20.500.12116/11103 Thu, 23 Jul 2026 19:58:31 GMT 2026-07-23T19:58:31Z http://dl.gi.de/handle/20.500.12116/11367 Leuchttürme und Durchlauferhitzer Hertzberg, Joachim Tue, 01 Jan 2013 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/11367 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/11356 News Tue, 01 Jan 2013 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/11356 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/11359 Statistic Methods for Path-Planning Algorithms Comparison Muñoz, Pablo; Barrero, David F.; R-Moreno, María D. The path-planning problem for autonomous mobile robots has been addressed by classical search techniques such as A* or, more recently, Theta* or S-Theta*. However, research usually focuses on reducing the length of the path or the processing time. The common practice in the literature is to report the run-time/length of the algorithm with means and, sometimes, some dispersion measure. However, this practice has several drawbacks, mainly due to the loose of valuable information that this reporting practice involves such as asymmetries in the run-time, or the shape of its distribution. Run-time analysis is a type of empirical tool that studies the time consumed by running an algorithm. This paper is an attempt to bring this tool to the path-planning community. To this end the paper reports an analysis of the run-time of the path-planning algorithms with a variety of problems of different degrees of complexity, indoors, outdoors and Mars surfaces. We conclude that the time required by these algorithms follows a lognormal distribution. Tue, 01 Jan 2013 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/11359 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/11368 Attention-Based Detection of Unknown Objects in a Situated Vision Framework Martín García, Germán; Frintrop, Simone; Cremers, Armin B. We present an attention-based approach for the detection of unknown objects in a 3D environment. The ability to address individual objects in the environment without having previous knowledge about their properties or their identity is one important requirement of the Situated Vision theory. Based on saliency maps, our attention system determines the regions where objects are likely to be found; these are the proto-objects whose extent is refined by a 2D segmentation step. At the same time a 3D scene model is built from measurements of a depth camera. The detected objects are projected into the 3D scene, resulting in 3D object models which are incrementally updated. We show the validity of our approach in an RGB-D sequence recorded in an office environment. Tue, 01 Jan 2013 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/11368 2013-01-01T00:00:00Z