D. Fox, "Markov localization: A probabilistic framework for mobile robot localization and navigation," Ph.D. dissertation, Univ. Bonn, Dept. Comput. Sci., Bonn, Germany, 1998.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....by the sensors on the robot. The latter initially starts with an empty map in an unknown environment and builds a representation of the environment from the actions carried out by the robot and the measurements of its sensors. For both problems, many solutions have been presented in the past [1, 4, 5, 8, 10, 13, 14]. In general, map building is the harder of the two problems since it requires to not only estimate the position of the robot but also the position of landmarks (walls, corners, etc. in the environment. In many cases special conditions might be needed when building a map such as having the ....

....be reformulated as a localization problem when arranging all maps in the database of environments into one global reference frame in such a way that no pair of environment maps overlap. Identifying the environment could then be solved by a global localization approach such as Markov Localization [1] where from the estimated pose the corresponding environment could be determined. Taking this point of view, map correlation as presented by Konolige and Chou [7] could be qualified as a related approach. In their work, the robot builds a patch (a small map) consisting of the last few frames of a ....

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, University of Bonn, Germany, 1998.

....we work with image sequences and use the stochastic approach exposed in the next section. 5. Probabilistic Localization The recognition problem is to find the right candidate among the potential hypotheses in a stream of images. We apply a probabilistic approach based on Markov localization [3] and factored sampling technique, called the conditional density propagation (CONDENSATION) which was originally developed in the context of visual tracking of curves in dense clutter [5, 6] It allows us to perform both localization and tracking of the target object through the camera motion. ....

....state density p t at time t is defined by p t (x t ) p(x t jZ t ) This represents all information about the state of the target object at time t that is deductible from the set Z t . The rule for propagation of state density [5] over time is similar to the Markov localization equations [3]: p(x t jZ t ) k t p(z t jx t ) p(x t jZ t 1 ) 4) where p(x t jZ t 1 ) Z x t 1 p(x t jx t 1 )p(x t 1 jZ t 1 ) dx t 1 (5) and k t is a normalization constant that does not depend on x t . The CONDENSATION algorithm is based on the factored sampling technique, which is a random sampling ....

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, Institute of Computer Science III, University of Bonn, Germany, 1998.

No context found.

Dieter Fox, Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation, Ph.D. thesis, University of Bonn, Bonn, Germany, December 1998.

No context found.

Dieter Fox, Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation, Ph.D. thesis, University of Bonn, Bonn, Germany, December 1998.

No context found.

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Naviagation. PhD thesis, Dept. of Computer Science, University of Bonn, Germany, December 1998.

No context found.

Dieter Fox, Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation, Ph.D. thesis, University of Bonn, Bonn, Germany, December 1998.

....The common reference frame needed to integrate the different maps is achieved by estimating the position of the robot relative to the static map. Robust position estimation in dynamic environments is attained by using a filter technique to detect sensor measurements corrupted by dynamic obstacles [Fox et al. 1998; Burgard et al. 1998] The techniques described in this paper have been imple mented and extensively tested. We used the mapping techniques to compute large scale maps of 3000m 2 containing large open spaces and long cycles. The map updating and sensor filtering techniques have been applied ....

....by filter techniques to detect measurements corrupted by non modeled, i.e. dynamic, obstacles. The resulting technique has been shown to be able to robustly estimate the position of mobile robots over long periods of time even in densely crowded environments such as museums and office environments [Fox et al. 1998; Fox, 1998; Burgard et al. 1998; Thrun et al. 1999] To allow the robot to react to unforeseen blockage of passages, the path planner consults the integrated map to determine shortest paths to arbitrary target points (see [Thrun, 1998] for a detailed description) Since this map is updated ....

[Article contains additional citation context not shown here]

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Naviagation. PhD thesis, Dept. of Computer Science, University of Bonn, Germany, December 1998.

....(color camera) and range finders for robot detection. 2. 1 Markov Localization Before turning to the topic of this paper collaborative multi robot localization let us first review a common approach to single robot localization, which our approach is built upon: Markov localization (see [11] for a detailed discussion) Markov localization uses only dead reckoning measurements a and environment measurements o; it ignores detections r. In the absence of detections (or similar information that ties the position of one robot to another) information gathered at different platforms cannot ....

....of being at location l after incorporating o (t) n is obtained by multiplying the observation likelihood P (o (t) n j L (t) n = l) with the prior belief. This likelihood is also called the environment perception model of robot n. Typical models for different types of sensors are described in [11, 9, 18]. 2. Odometry: Now suppose the last item in d (t) n is an odometry measurement, denoted a (t) n . Using the Theorem of Total Probability and exploiting the Markov property, we obtain the following incremental update scheme: Bel (t) n (L = l) Gamma Z P (L (t) n = l j a (t Gamma1) n ....

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Naviagation. PhD thesis, Dept. of Computer Science, University of Bonn, Germany, December 1998.

....we will begin with an intuitive description of Markov localization, followed by a mathematical derivation of the algorithm. The reader may notice that Markov localization is a special case of probabilistic state estimation, applied to mobile robot localization (see also Russell Norvig, 1995; Fox, 1998 and Koenig Simmons, 1998) For clarity of the presentation, we will initially make the restrictive assumption that the environment is static. This assumption, called Markov assumption, is commonly made in the robotics literature. It postulates that the robot s location is the only state in the ....

....mainly di er in their eciency and how they model the characteristics of the sensors and the map of the environment. In order to combine the strengths of the previous representations, our approach relies on a ne and less restrictive representation of the state space (Burgard et al. 1996, 1998b; Fox, 1998). Here the robot s belief is approximated by a ne grained, regularly spaced grid, where the spatial resolution is usually between 10 and 40 cm and the angular resolution is usually 2 or 5 degrees. The advantage of this approach compared to the Kalman lter based techniques is its ability to ....

[Article contains additional citation context not shown here]

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Naviagation. PhD thesis, Dept. of Computer Science, University of Bonn, Germany, December 1998.

....we will begin with an intuitive description of Markov localization, followed by a mathematical derivation of the algorithm. The reader may notice that Markov localization is a special case of probabilistic state estimation, applied to mobile robot localization (see also Russell Norvig, 1995; Fox, 1998 and Koenig Simmons, 1998) For clarity of the presentation, we will initially make the restrictive assumption that the environment is static. This assumption, called Markov assumption, is commonly made in the robotics literature. It postulates that the robot s location is the only state in the ....

....mainly di er in their eciency and how they model the characteristics of the sensors and the map of the environment. In order to combine the strengths of the previous representations, our approach relies on a ne and less restrictive representation of the state space (Burgard et al. 1996, 1998b; Fox, 1998). Here the robot s belief is approximated by a ne grained, regularly spaced grid, where the spatial resolution is usually between 10 and 40 cm and the angular resolution is usually 2 or 5 degrees. The advantage of this approach compared to the Kalman lter based techniques is its ability to ....

[Article contains additional citation context not shown here]

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Naviagation. PhD thesis, Dept. of Computer Science, University of Bonn, Germany, December 1998.

....this model is shown in Figure 2. Shown there is the probability of a sonar reading (vertical axis) as a function of the correct distance (determined using ray tracing) and the measured distance. The graph in Figure 2 has been generated from several millions of raw sonar readings (see [FBT98, Fox98] It is the result of fitting a model consisting of a mixture of of a linearGaussian (centered around the correct distance) a Geometric distribution (modeling overly short readings) and a Dirac distribution (modeling max range readings) to this data. ffl The inverse perception model is denoted ....

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, Dept of Computer Science, Univ. of Bonn, Germany, 1998.

....P (s t j l) it remains to determine the probability P (s t j o l ) of measuring the value s t given the expected distance o l . In our approach, the density P (s j o l ) is defined as a mixture of a Gaussian density centered around the expected distance o l and a geometric distribution [17,11]. The geometric distribution is designed to allow the system to deal with a certain amount of un modelled objects such as people walking by. In order to determine the parameters of this model we collected several million data pairs consisting of the expected distance o l and the measured distance ....

....objects. Based on this technique, Minerva was able to operate reliably over a period of 13 days. During that time over 50.000 people were in the museum and watched or interacted with the robot. At all Minerva travelled 44km with a maximum speed of 1.63m sec. In an extensive experimental comparison [14,11] it has been demonstrated that both filters significantly improve the robustness of the localization process especially in the presence of large amounts of sensor noise. 4.2 Probabilistic Integration of Map Information into a Reactive Collision Avoidance System During the deployments of Rhino and ....

[Article contains additional citation context not shown here]

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, Dept of Computer Science, Univ. of Bonn, Germany, 1998.

....the world model, and the y axis is the distance o n measured by the sensor. The function is a mixture of a Gaussian density and a geometric distribution. It integrates the accuracy of the sensor with the likelihood of receiving a random measurement (e.g. due to obstacles not modeled in the map [22]) A Monte Carlo Algorithm for Multi Robot Localization 5 100 200 300 400 100 200 300 400 500 0 0.1 0.2 0.3 0.4 expected distance [cm] measured distance [cm] probability Fig. 1: Perception model for laser range finders. The x axis depicts the expected measurement, the y axis the measured ....

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Naviagation. PhD thesis, Department of Computer Science, University of Bonn, Germany, December 1998.

....in the excess of 100MB, and highperformance computing. At the other extreme, various researchers have resorted to coarse grained topological representations, whose granularity is often an order of magnitude lower than that of the grid based approach. When high resolution is needed (see e.g. (Fox et al. 1998), who uses localization to avoid collisions with static obstacles that cannot be detected by sensors) such approaches are inapplicable. In this paper we present Monte Carlo Localization (in short: MCL) Monte Carlo methods were introduced in the Seventies (Handschin 1970) and recently ....

....basic Markov localization algorithm upon which our approach is based. The key idea of Markov localization which has recently been applied with great success at various sites (Nourbakhsh, Powers, Birchfield 1995; Simmons Koenig 1995; Kaelbling, Cassandra, Kurien 1996; Burgard et al. 1996; Fox 1998) is to compute a probability distribution over all possible positions in the environment. Let l = hx; y; i denote a position in the state space of the robot, where x and y are the robot s coordinates in a world centered Cartesian reference frame, and is the robot s orientation. The ....

[Article contains additional citation context not shown here]

Fox, D. 1998. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Naviagation. Ph.D. Diss, University of Bonn, Germany.

No context found.

D. Fox, "Markov localization: A probabilistic framework for mobile robot localization and navigation," Ph.D. dissertation, Univ. Bonn, Dept. Comput. Sci., Bonn, Germany, 1998.

No context found.

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, Institute of Computer Science III, University of Bonn, Germany, December 1998.

No context found.

Fox, D.: Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, Institute of Computer Science, TU Dreseden, Germany (1998)

No context found.

Dieter Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, Institute of Computer Science III, University of Bonn, Germany, 1998.

No context found.

D. Fox, "Markov localization: A probabilistic framework for mobile robot localization and naviagation," Ph.D. dissertation, Dept. of Computer Science, University of Bonn, Germany, December 1998.

No context found.

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, Institute of Computer Science III, University of Bonn, Germany, December 1998.

No context found.

Dieter Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, University of Bonn, Bonn, Germany, December 1998.

No context found.

Dieter Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, University of Bonn, Bonn, Germany, December 1998.

No context found.

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, University of Bonn, Bonn, Germany, December 1998.

No context found.

Fox, Dieter (1998). Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis. University of Bonn. Bonn, Germany.

No context found.

D. Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, University of Bonn, Bonn, Germany, December 1998.

No context found.

D. Fox, "Markov localization: A probabilistic framework for mobile robot localization and naviagation," Ph.D. dissertation, Institute of Computer Science III, University of Bonn, 1998.

No context found.

Dieter Fox. Markov Localization: A Probabilistic Framework for Mobile Robot Localization and Navigation. PhD thesis, Institute of Computer Science, University of Bonn, Germany, 1998.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC