Tom Duckett and Ulrich Nehmzow. Knowing your place in real world environments. In Proceedings of EUROBOT '99, 3rd European Workshop on Advanced Mobile Robots, pages 135-142. IEEE Computer Press, 1999.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....executed actions. It is one of the fundamental problems in mobile robot navigation and many solutions have been presented in the past including approaches employing Kalman filtering [14, 15, 17, 18] grid based Markov localization [4, 10] or Monte Carlo methods [9, 16, 20] For an overview see [7, 11, 19]. By performing localization experiments with a mobile robot it has been ascertained that grid based Markov localization is more robust than Kalman filtering while the latter given good inputs is more efficient and accurate than the former [13] A combination of both approaches is likely to ....

T. Duckett and U. Nehmzow. Knowing your place in real world environments. In European Workshop on Advanced Mobile Robots (EUROBOT'99), 1999.

No context found.

Tom Duckett and Ulrich Nehmzow. Knowing your place in real world environments. In Proceedings of EUROBOT '99, 3rd European Workshop on Advanced Mobile Robots, pages 135-142. IEEE Computer Press, 1999.

....level as predictor of viable homing data was the rst SOFM value on path 3 ( gure 7) There is no obvious perceptual aliasing at this position, maybe the con guration of the environment at this place created some incorrect sonar reading. Although over reliance on odometry can create problems [2], basing movement on odometry during the learning phase presented none. The robot su ered from a small degree of odometric drift during learning, this was only translational and not rotational because the uxgate compass removed any drift error. The experiment investigated how a complex ....

T. Duckett and U. Nehmzow. Knowing your place in real world environments. In EUROBOT'99: 3rd European Workshop on Advanced Mobile Robots. IEEE Computer Society Press, 1999.

....landmark recognition by a navigating mobile robot, especially in situations where computational cost matters. In ongoing work, we have successfully applied this new technique in a complete navigation system which uses previous location information to further improve selflocalisation performance (Duckett Nehmzow 1999). Acknowledgements This work was carried out as part of the rst named author s PhD thesis at the University of Manchester, who gratefully acknowledges a studentship provided by the Department of Computer Science. ....

Duckett, T., and Nehmzow, U. 1999. Knowing your place in real world environments. In Proc. EUROBOT '99, 135-142. IEEE Computer Press. Online at http://www.cs.man.ac.uk/~duckettt.

....only the local metric relations between places. In this paper, we assume that the robot has the ability to determine its orientation using a compass, and the ability to recognise its own place in the map. Full details of the self localisation mechanism used in these experiments can be found in [4]. 1.1 Previous Work Lu and Milios [8] considered the problem of enforcing geometric consistency in a metric map. Their approach maintained a history of all the local frames of sensor data used to construct the map and the network of spatial relations between the frames. The spatial relations ....

T. Duckett and U. Nehmzow. Knowing your place in real world environments. In Proc. EUROBOT '99, 3rd European Workshop on Advanced Mobile Robots. IEEE Computer Society Press, 1999.

.... sensor data with those stored previously in the map to find the best matching place (as in Weiss and Puttkamer [17] Using histograms requires only a fraction of the storage and processing required to compare whole occupancy grids, with little or no loss in overall information content (see [6] for full details) However, due to problems such as perceptual aliasing and sensor noise, the best matching place is not guaranteed to be the true location of the robot. To overcome these problems, we developed an iterative localisation algorithm (see [5, 6] for details) Here, the robot ....

....loss in overall information content (see [6] for full details) However, due to problems such as perceptual aliasing and sensor noise, the best matching place is not guaranteed to be the true location of the robot. To overcome these problems, we developed an iterative localisation algorithm (see [5, 6] for details) Here, the robot maintains a multi modal probability distribution over a set of possible location hypotheses , reflecting the robot s confidence in its estimate of its position. As the robot moves through its environment, this probability distribution is updated on the basis of the ....

[Article contains additional citation context not shown here]

T. Duckett and U. Nehmzow, Knowing Your Place in Real World Environments, submitted to EUROBOT-99, 1999.

....landmark recognition by a navigating mobile robot, especially in situations where computational cost matters. In ongoing work, we have successfully applied this new technique in a complete navigation system which uses previous location information to further improve selflocalisation performance (Duckett Nehmzow 1999). Acknowledgements This work was carried out as part of the first named author s PhD thesis at the University of Manchester, who gratefully acknowledges a studentship provided by the Department of Computer Science. ....

Duckett, T., and Nehmzow, U. 1999. Knowing your place in real world environments. In Proc. EUROBOT '99, 135--142. IEEE Computer Press. Online at http://www.cs.man.ac.uk/~duckettt.

....thereby eliminating the need for off line processing and increasing the autonomy of the robot. In this paper, we assume that the robot has the ability to determine its own location in the topological map; full details of the self localisation mechanism used in these experiments can be found in [3]. 1.1 Related Work Yamauchi [18] developed a technique called frontierbased exploration, in which a global occupancy grid [11] was used to represent the environment. Image segmentation techniques were used to extract regions in the grid between charted and unknown territory known as ....

....in the map have either been visited by the robot or deleted. In order to implement this exploration strategy, the following mechanisms were required: 1. Location Recognition. We assume that the robot has the ability to locate itself within the map. The selflocalisation algorithm described in [3] was used here; this algorithm is able to determine the most likely place occupied by the robot, and also the most likely displacement of the robot within each of the possible places. 2. Open Space Detection and Compass Sense. In order to add the new predicted places to the map, the robot ....

[Article contains additional citation context not shown here]

T. Duckett and U. Nehmzow. Knowing your place in real world environments. In EUROBOT '99, 3rd European Workshop on Advanced Mobile Robots. IEEE Computer Society Press, 1999.

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