W. Burgard, A. Derr, D. Fox, and A. B. Cremers. Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach. In Proceedings of the IEEE/RSJ International Conference on Intelligent RObot and Systems, 1998. 10 Lazkano et al.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....time as staying within the framework of the well understood Kalman filter. This paper focuses on what in [5] is called CONDENSATION and later in [6] Monte Carlo Localization (MCL) The key idea is to use a set of samples to represent the PDF encoding the robots knowledge about its position. In [7] a grid was used to represent the PDF, the drawback of this being the tradeoff between accuracy and computational effort to keep it updated. For large search spaces where the probability density is low over much of the space, a sample based representation is more efficient [6] For the set of ....

W. Burgard, A. Derr, D. Fox, and A. Cremers, "Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach," in Proc. of the Intl. Symposium on Intelligent Robotic Sys- tems, 1998.

....approach can deal with noisy sensor data as well as handle ambiguities, but, when applied to ne grained grids, could be very expensive under the com putational point of view. In order to overcome the problems deriving from huge search space, these techniques use to include several optimizations [17]; the most frequent of which is to update only the data in a small area around the robot Recently, sampling based methods have gained increasing interest, in particular Monte Carlo Localization [18] This approach does not base on an explicit description of the probability density, but it ....

Burgard, W., Derr, A., Fox, D., Cremers, A.: Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach. In: proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). (1998)

....under global uncertainty, i.e. to recover from becoming lost. The rst problem is well understood, and a number of successful approaches have been applied to the second problem in recent years. However, few systems can deal eciently with both one exception is the approach of Burgard et al. [2], which uses a variable resolution metric map to handle varying degrees of uncertainty in the robot s location estimates. While ecient solutions have been found for metric maps, topological maps have, by nature of their compactness, the potential for representing environments which are several ....

....solve the global localisation problem in environments with high levels of perceptual aliasing. A variety of methods have been proposed for resolving perceptual ambiguity by accumulating sensory evidence over time. The most popular is the probabilistic approach known as Markov localisation (e.g. [2, 5, 7, 8], etc. which can be applied to either topological or metric maps. The main paradigm for probabilistic navigation using topological maps is that of Hidden Markov Models, and their extension to Partially Observable Markov Decision Processes [7, 8] Here, the robot maintains a probability ....

[Article contains additional citation context not shown here]

W. Burgard, A. Derr, D. Fox, and A. B. Cremers, Integrating Global Position Estimation and Position Tracking for Mobile Robots: The Dynamic Markov Localization Approach, Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, 1998.

....uncertainty, e.g. to recover from becoming lost. The rst problem is well understood, and a number of successful approaches have been applied to the second problem in recent years. However, few systems can deal with both problems in real time one exception is the approach of Burgard et al. [3], which uses a variable resolution metric map to handle varying degrees of uncertainty in the robot s location estimates. While successful navigation systems have been developed using metric maps, topological maps have, by nature of their compactness, the potential for representing environments ....

....in environments with high levels of perceptual aliasing. A variety of methods have been proposed for resolving perceptual ambiguity by incorporating previous location information into the recognition of locations. The most popular is the probabilistic approach known as Markov localisation (e.g. [3, 10, 13, 17], etc. which can be applied to either topological or metric maps. The main paradigm for probabilistic navigation using topological maps is that of Hidden Markov Models, and their extension to Partially Observable Markov Decision Processes [13, 17] Here, the robot maintains a probability ....

[Article contains additional citation context not shown here]

Wolfram Burgard, Andreas Derr, Dieter Fox, and Armin B. Cremers. Integrating global position estimation and position tracking for mobile robots: The dynamic Markov localization approach. In Proceedings of the 18 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'98), Victoria, Canada, 1998.

....uncertainty, e.g. to recover from becoming lost. The first problem is well understood, and a number of successful approaches have been applied to the second problem in recent years. However, few systems can deal with both problems in real time one exception is the approach of Burgard et al. [3], which uses a variable resolution metric map to handle varying degrees of uncertainty in the robot s location estimates. 0921 8890 01 see front matter 2001 Elsevier Science B.V. All rights reserved. PII: S0921 8890(00)00116 0 118 T. Duckett, U. Nehmzow Robotics and Autonomous Systems 34 ....

....in environments with high levels of perceptual aliasing. A variety of methods have been proposed for resolving perceptual ambiguity by incorporating previous location information into the recognition of locations. The most popular is the probabilistic approach known as Markov localisation (e.g. [3,10,13,17], etc. which can be applied to either topological or metric maps. The main paradigm for probabilistic navigation using topological maps is that of Hidden Markov Models, and their extension to Partially Observable Markov Decision Processes [13,17] Here, the robot maintains a probability ....

[Article contains additional citation context not shown here]

W. Burgard, A. Derr, D. Fox, A.B. Cremers, Integrating global position estimation and position tracking for mobile robots: The dynamic Markov localization approach, in: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'98), Victoria, BC, 1998.

....of embedding Kalman filters in a Markov model follows the principles underlying multiple hypothesis tracking for state estimation in switching environments. Other related work includes approaches improving the efficiency and accuracy of Markov localization. For instance dynamic Markov localization [5] is a fine grained grid based Markov localization method which selectively updates the likely parts of the belief state, and dynamically modifies the grain of the quantization to adjust to the certainty of the current location. This technique is more general and uniform than ours. However, our ....

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating Global Position Estimation and Position Tracking for Mobile Robots: The Dynamic Markov Localization Approach. In Proc. IROS-98, 1998.

No context found.

W. Burgard, A. Derr, D. Fox, and A. B. Cremers. Integrating global position estimation and position tracking for mobile robots: the Dynamic Markov Localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 1998.

No context found.

Wolfram Burgard, Andreas Derr, Dieter Fox, and Armin B. Cremers. Integrating global position estimation and position tracking for mobile robots: The dynamic markov localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'98), 1998.

....robot localization. In robot localization, the task is to estimate the position of a mobile robot based on a map and sensor data collected by the robot [51] Over the last years, we investigated several variants of dynamic Bayes filters in the context of robot localization and people tracking [21, 20, 49, 47, 51, 137]. In various experiments we demonstrated the advantages of rich, non parametric representations over more restricted representations such as Gaussians used in Kalman filters [58, 59, 98] As a consequence of this research, we introduced particle filters [41] as a powerful tool for state estimation ....

W. Burgard, A. Derr, D. Fox, and A. B. Cremers. Integrating global position estimation and position tracking for mobile robots: the Dynamic Markov Localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 1998.

....compensate incremental errors in a robot s odometry. Algorithms for position tracking often make restrictive assumptions on the size of the error and the shape of the robot s uncertainty, required by a range of existing localization algorithms. More challenging is the global localization problem [6,34,61], where a robot is not told its initial pose but instead has to determine it from scratch. The global localization problem is more difficult, since the error in the robot s estimate cannot be assumed to be small. Consequently, a robot should be able to handle multiple, distinct hypotheses. Even ....

....[7,24] However, accommodating raw sensor data requires fine grained representations, which impose significant computational burdens. To overcome this limitation, researchers have proposed selective updating algorithms [24] and tree based representations that dynamically change their resolution [6]. It is remarkable that all of these algorithms share the same probabilistic basis. They all estimate posterior distributions over poses under certain independence assumptions which will also be the case for the approach presented in this article. This article presents a probabilistic ....

[Article contains additional citation context not shown here]

W. Burgard, A. Derr, D. Fox, A.B. Cremers, Integrating global position estimation and position tracking for mobile robots: The dynamic markov localization approach, in: Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'98), Victoria, BC, 1998.

....realization In the previous section we left open how to represent the beliefs p(l) and p(s) of the robot s position and the state of the object. Over the past years, different techniques have been used to represent the beliefs. Among them are piecewise constant approximations as applied in [3,4,12,15,19,25]. A very popular approach is to use Gaussians [10,16,24,26] to represent the densities. In this paper we use particle filters to approximate the involved densities. The key idea of particle filters is to use a sample based representation for the densities. The updates are carried out using ....

W. Burgard, A. Derr, D. Fox, A.B. Cremers, Integrating global position estimation and position tracking for mobile robots: The dynamic Markov localization approach, in: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1998.

....rough sense as to where the robot is. Grid based Markov localization. To deal with multi modal and non Gaussian densities at a fine resolution (as opposed to the coarser discretization in the above methods) grid based approaches perform numerical integration over an evenly spaced grid of points [5, 34, 6]. This involves discretizing the interesting part of the state space, and use it as the basis for an approximation of the state space density, e.g. by a piece wise constant function. Grid based methods are powerful, but suffer from excessive computational overhead and a priori commitment to the ....

....computational overhead and a priori commitment to the size and resolution of the state space. The computational requirements have an effect on accuracy as well, as not all measurements can be processed in real time, and valuable information about the state is thereby discarded. Recent work [34] has begun to address these problems, using oct trees to obtain a variable resolution representation of the state space. This has the advantage of concentrating the computation and memory usage where needed, and addresses the limitations arising from fixed resolutions. The issue of cooperation ....

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating global position estimation and position tracking for mobile robots: the Dynamic Markov Localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1998.

....additional assumptions necessary for factorial representations of joint probability distributions as explained further below. Throughout this paper, we adopt a probabilistic approach to localization. Probabilistic methods have been applied with remarkable success to single robot localization [51, 62, 34, 9, 23, 8, 29], where they have been demonstrated to solve problems like global localization and localization in dense crowds. 2.1 Data Let be the number of robots, and let denote the data gathered by the th robot, with . Obviously, each is a sequence of three different types of ....

....local ones: First, the initial location of the robot does not have to be specified and, second, they provide an additional level of robustness, due to their ability to recover from localization failures. Among the global approaches those using metric representations of the space such as MCL and [9, 8, 39] can deal with a wider variety of environments than those methods relying on topological maps. For example, they are not restricted to orthogonal environments containing pre defined features such as corridors, intersections and doors. In addition, most existing approaches are restricted in the ....

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating global position estimation and position tracking for mobile robots: the Dynamic Markov Localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1998.

....to Elsevier Preprint 3 December 2000 odometry. Algorithms for position tracking often make restrictive assumptions on the size of the error and the shape of the robot s uncertainty, required by a range of existing localization algorithms. More challenging is the global localization problem [4], where a robot is not told its initial pose, but instead has to determine it from scratch. The global localization problem is more difficult, since the error in the robot s estimate cannot be assumed to be small. Here a robot should be able to handle multiple, distinct hypotheses. Even more ....

....the piecewise constant representation can impose a significant computational burden, especially if one is interested in high resolution. To overcome this limitation, researchers have proposed selective updating algorithms [21] and tree based representations that dynamically change their resolution [4]. While these algorithms work well in real time, they nevertheless suffer two limitations: First, they are computationally very expensive, and second, the accuracy is limited by the resolution of the approximation, which typically lacks behind that of Kalman filters when a robot is well localized ....

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating global position estimation and position tracking for mobile robots: The dynamic markov localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'98), 1998. To appear.

....local ones: First, the initial location of the robot does not have to be specified and, second, they provide an additional level of robustness, due to their ability to recover from localization failures. Among the global approaches those using metric representations of the space such as MCL and [6, 5] can deal with a wider variety of environments than the methods relying on topological maps. For example, they are not restricted to orthogonal environments containing pre defined features such as corridors, intersections and doors. The issue of cooperation between multiple mobile robots has ....

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating global position estimation and position tracking for mobile robots: the Dynamic Markov Localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1998.

....#### ## ### ######### ##### ####### ## ##### ### ##### ## #### #### ## ### #### ####### ##### 392 Markov Localization for Mobile Robots in Dynamic Environments ### ### Fig. 1. The mobile robots Rhino (a) and Minerva (b) acting as interactivemuseum tour guides. tive museum tour guide robots (Burgard et al. 1998a, 2000; Thrun et al. 1999) in the Deutsches Museum Bonn and the National Museum of American History in Washington, DC, respectively. Experiments described in this paper illustrate the abilityofour Markov localization technique to deal with approximate models of the environment, such as occupancy ....

....environment are not covered by the world model. This is the case, for example, in densely crowded environments, where groups of people cover the robots sensors and thus lead to many unexpected measurements. The mobile robots Rhino and Minerva, whichwere deployed as interactivemuseum tour guides (Burgard et al. 1998a, 2000; Thrun et al. 1999) were permanently faced with such a situation. Figure 7 404 Markov Localization for Mobile Robots in Dynamic Environments RHINO ### ### Fig. 7. Rhino surrounded by visitors in the ######### ###### ####. ### ### Fig. 8. Typical laser scans obtained when Rhino is ....

[Article contains additional citation context not shown here]

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating global position estimation and position tracking for mobile robots: the Dynamic Markov Localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1998.

....additional assumptions necessary for factorial representations of joint probability distributions as explained further below. Throughout this paper, we adopt a probabilistic approach to localization. Probabilistic methods have been applied with remarkable success to single robot localization [51, 62, 34, 9, 23, 8, 29], where they have been demonstrated to solve problems like global localization and localization in dense crowds. 2.1 Data Let N be the number of robots, and let d n denote the data gathered by the n th robot, with 1 n N . Obviously, each d n is a sequence of three different types of ....

....local ones: First, the initial location of the robot does not have to be specified and, second, they provide an additional level of robustness, due to their ability to recover from localization failures. Among the global approaches those using metric representations of the space such as MCL and [9, 8, 39] can deal with a wider variety of environments than those methods relying on topological maps. For example, they are not restricted to orthogonal environments containing pre defined features such as corridors, intersections and doors. In addition, most existing approaches are restricted in the ....

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating global position estimation and position tracking for mobile robots: the Dynamic Markov Localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1998.

....case of the kidnapped robot problem in which the robot is told that it has been carried away. 392 Markov Localization for Mobile Robots in Dynamic Environments (a) b) Fig. 1. The mobile robots Rhino (a) and Minerva (b) acting as interactive museum tour guides. tive museum tour guide robots (Burgard et al. 1998a, 2000; Thrun et al. 1999) in the Deutsches Museum Bonn and the National Museum of American History in Washington, DC, respectively. Experiments described in this paper illustrate the ability of our Markov localization technique to deal with approximate models of the environment, such as ....

....environment are not covered by the world model. This is the case, for example, in densely crowded environments, where groups of people cover the robots sensors and thus lead to many unexpected measurements. The mobile robots Rhino and Minerva, which were deployed as interactive museum tour guides (Burgard et al. 1998a, 2000; Thrun et al. 1999) were permanently faced with such a situation. Figure 7 404 Markov Localization for Mobile Robots in Dynamic Environments RHINO (a) b) Fig. 7. Rhino surrounded by visitors in the Deutsches Museum Bonn. a) b) Fig. 8. Typical laser scans obtained when Rhino is ....

[Article contains additional citation context not shown here]

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating global position estimation and position tracking for mobile robots: the Dynamic Markov Localization approach. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1998.

No context found.

W. Burgard, A. Derr, D. Fox, and A. B. Cremers. Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach. In Proceedings of the IEEE/RSJ International Conference on Intelligent RObot and Systems, 1998. 10 Lazkano et al.

No context found.

Burgard, W., Derr, A., Fox, D., and Cremers, A. B. (1998). Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach. In Proceedings of the IEEE/RSJ International Conference on Intelligent RObot and Systems.

No context found.

Burgard, Wolfram, Andreas Derr, Dieter Fox and Armin Cremers (1998). Integrating global position estimation and position tracking for mobile robots. In: Proceedings of IROS-98.

No context found.

W. Burgard, A. Derr, D. Fox, and A. B. Cremers. Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach. In Proceedings of the IEEE/RSJ International Conference on Intelligent RObot and Systems, 1998. 10 Lazkano et al.

No context found.

W. Burgard, A. Derr, D. Fox, and A. Cremers, \Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach," in Proc. of the Intl. Symposium on Intelligent Robotic Systems, 1998.

No context found.

W. Burgard, A. Derr, D. Fox, and A.B. Cremers. Integrating global position estimation and position tracking for mobile robots: The dynamic markov localization approach. In IEEE/RSJ International Conference on Intelligent Robots and Systems, 1998.

No context found.

W. Burgard, A. Derr, D. Fox, and A. Cremers. Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach. In proceedings of International Conference on Intelligent Robots and Systems (IROS), 1998.

First 50 documents

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