Using the CONDENSATION algorithm for robust, vision-based mobile robot localization

By Frank Dellaert, Wolfram Burgard, Dieter Fox, Sebastian Thrun. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Filtering with State-Observation Examples via Kernel Monte Carlo Filter (2013, background): “east in a parametric form. This can be a limitation for real world problems for which the observation model is not easily given. Consider for example a vision-based mobile robot localization problem (Dellaert et al., 1999), where the state xt is the position of a robot in a map and the observation z”
Factor Graphs and GTSAM: A Hands-on Introduction (2012, background): “Such unary factors are applicable for measurements z t that only depend on the current robot pose, e.g., GPS readings, correlation of a laser range-finder in a pre-existing map, or indeed the presence of absence of ceiling lights, see Dellaert et al. (1999) for that amusing example.”
Data fusion for visual tracking with particles (2004, unknown): “See examples in [7], [13], [14], [26], [28], [41], [43], [45], [46], [48], [49].”
Monte Carlo Filtering Using Kernel Embedding of Distributions (2014, background): “For example, consider localization of a mobile robot from its vision images (Dellaert et al. 1999; Se, Lowe, and Little 2001).”
Probabilistic Algorithms and the Interactive Museum Tour-Guide Robot Minerva (2000, background): “The MCL algorithm is in fact quite e cient [34, 35, 48]; slight modi cations of the basic algorithms [48, 83, 145] require only a few hundred samples for reliable localization,”
Vision-based global localization and mapping for mobile robots (2005, methodology): “For the brightness measurements in [ 8 ], stochastic localization methods are required to localize the robot gradually while it moves around.”
A Probabilistic On-Line Mapping Algorithm for Teams of Mobile Robots (2001, methodology): “However, MCL can be applied if it is known that one robot starts in the map built by another.”
Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual Landmarks (2002, methodology): “However, it does not scale to large environments as the calculation cost of the posterior probability is too expensive.”
Active localization with dynamic obstacles (2016, methodology): “We employ a particle ﬁlter [18], [19], [20] to solve the passive global localization problem.”
Robust Monte Carlo localization for mobile robots (2001, methodology): “Similar results were obtained using a camera as the primary sensor for localization [12].”
Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization (2005, methodology): “Dellaert et al. [16], [17] match images obtained with a camera pointed to the ceiling to a large ceiling mosaic covering the whole operational space of the robot.”
Towards programming tools for robots that integrate probabilistic computation and learning (2000, methodology): “The reader may notice that such sample-based approximations have been applied with great success in robotics [4, 7] and computer vision??.”
Monocular vision SLAM for indoor aerial vehicles (2009, unknown): “SLAM [ 11 ] show very successful localization performance.”
Adapting the Sample Size in Particle Filters Through KLD-Sampling (2003, background): “Particle filters have been applied to a variety of robot platforms and sensors such as vision (Dellaert et al. 1999; Lenser and Veloso 2000; Enderle et al. 2000; Wolf, Burgard, and Burkhardt 2002; Vlassis, Terwijn, and Kröse 2002; Gutmann and Fox 2002) and proximity sensors (Fox et al. 1999a, 2001;…”
Vision-based mobile robot localization and mapping using scale-invariant features (2001, methodology): “The Monte Carlo Localization method was proposed in [5] based on the CONDENSATION algorithm [9].”
Simultaneous Localization, Mapping and Moving Object Tracking (2007, methodology): “If we have a stationary object map in advance, map-based localization techniques (Olson 2000 Fox et al., 1999 Dellaert et al., 1999) can be used to increase the accuracy of the pose estimate.”
Map-Based Precision Vehicle Localization in Urban Environments (2007, background): “Urban environments are dynamic, and for localization to succeed one has to distinguish static aspects of the world (e.g., the road surface) relative to dynamic aspects (e.g., cars driving by).”