| A. J. Davison. Mobile robot navigation using active vision. PhD thesis, University of Oxford, 1999. |
....unknown environ ment. I. MOTIVATION This paper describes a method that enables a robot using feature based navigation techniques to autonomously explore its environment. Recently, there has been much written about feature based Simulta neous Localization and Mapping (SLAM) algorithms [1] 2] [3], 4] 5] Such algorithms attempt to answer the question where am I and what is around me . That answered the next obvious question is where should I go next . The exploration algorithm presented in this paper provides a sensible answer to this question. In [4] an indoor mobile robot was ....
A.J. Davison, Mobile Robot Navigation Using Active Vi- sion, Ph.D. thesis, University of Oxford, 1998.
....[4] Considerable recent research effort has been extended toward mitigation of the ) complexity (where n is the number of features) of the Kalman filter SLAM solution. Efficient strategies for SLAM with feature based representations and Gaussian representation of error include postponement [2], decoupled stochastic mapping [10] the compressed filter [6] sequential map joining [15] the constrained local submap filter [18] and sparse extended information filters [17] Each of these methods employs a single, globally referenced coordinate frame for state estimation. The Kalman filter ....
A. J. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1998.
.... This includes some methods implemented and tested at Oxford Testing has been mostly for purposes of illustration, rather than rigorous analysis 2 Notation As is standard, vectors will appear in bold type (x,y) and matrices in teletype (M,P) Map building notation will be as in Davisoh s thesis [5] which details the system and basic algorithm used for testing. In summary, that is as follows: X z State vector consisting of vehicle state and feature states. The v subscript is dropped from xv where it is not ambiguous. Pxx Pyx Py. x PXyl Pyy Pyy Pxy2 Pyy Pyy Symmetric covariance ....
.... noise 3 The Extended Kalman Filter in SLAM Since most typical vehicle models are non linear, the extended version of the Kalman Filter must be used (and anyway it applies equally well if the model is linear) The prediction and update equations are stated here without proof or explanation, see [5] or other literature if not already au fait with them. 3.1 The Raw Equations Prediction Our state and covariance predictions at time k I are based on those at time k and use the state transition function f and its Jacobian, control inputs u, and the process noise covariance. Update The ....
[Article contains additional citation context not shown here]
Andrew Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, Robotics Research Group, Oxford University Department of Engineering Science, February 1998. Available from www. robots. ox. ac. uk/~aj d/.
....points, and its use of dynamic programming for efficient 3D line tracking. We show preliminary results from the system for both indoor and outdoor sequences. 1. INTRODUCTION There is increasing interest in the development of structure from motion (SFM) algorithms capable of running in realtime [5, 6]. Real time SFM will enable applications such as (1) real time navigation of mobile robots in unknown environments, 2) real time capture of 3 D computer models using hand held cameras, and (3) real time head tracking in extended environments. This paper presents a system that uses vanishing ....
.... scene structure to a common reference frame defined by the initial camera pose, as in the work in robotics known as simultaneous localization and mapping (SLAM) 9, 10, 11, 8] using laser range scanners [10, 12, 11, 13] Some vision researchers have pursued similar approaches for limited scenes [5, 14]. 2. THE ALGORITHM VPs intersection line tracks clusters rotation updates translation updates edges 3D lines Fig. 1. Data Flow Graph. Figure 1 summarizes the data flow in our system. Given a sequence of omni directional images and detected linear features, our task is to estimate the 3D ....
Davison, A.J.: Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford (1998)
.... the importance of maintaining spatial correlations to achieve consistent error bounds [7, 8] The representation of spatial correlations results in an growth in computational cost [4] motivating techniques to address the map scaling problem through spatial and temporal partitioning [9, 10, 11]. Almost all implementations of feature based CML to date have used fairly simple nearest neighbor gating techniques. A more powerful technique that tests the Joint Compatibility testing of multiple sensor measurements, using a branch and bound algorithm, has been developed by Neira and Tardos ....
A. J. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1998.
No context found.
A.J.Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1998. Available at http://www.robots.ox.ac.uk/ajd/.
No context found.
A. J. Davison, Mobile Robot Navigation Using Active Vision, Ph.D. thesis, University of Oxford, 1998, Available at http://www.robots.ox.ac.uk/ajd/.
No context found.
A. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, Robotics Research Group, Oxford University Department of Engineering Science, Feb. 1998. Full text available at www.robots.ox.ac.uk/~ajd/.
No context found.
A. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, Robotics Research Group, Oxford University Department of Engineering Science, Feb. 1998. Full text available at www.robots.ox.ac.uk/~ajd/.
No context found.
A.J.Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1998. Available at http://www.robots.ox.ac.uk/ajd/.
No context found.
A.J. Davison, Mobile robot navigation using active vision, Ph.D. Thesis, University of Oxford, 1998. http://www.robots.ox.ac.uk/ # ajd/.
No context found.
A. J. Davison, Mobile Robot Navigation Using Active Vision, Ph.D. thesis, University of Oxford, 1998, Available at http://www.robots.ox.ac.uk/ajd/.
No context found.
A.J.Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1998. Available at http://www.robots.ox.ac.uk/ajd/.
No context found.
A. J. Davison. Mobile robot navigation using active vision. PhD thesis, University of Oxford, 1999.
No context found.
A. J. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1999.
No context found.
A. J. Davison. Mobile robot navigation using active vision. PhD thesis, University of Oxford, 1999.
No context found.
A. J. Davison. Mobile Robot Navigation using Active Vision. PhD thesis, Oxford University, 1998.
No context found.
A. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1998.
No context found.
A. J. Davison. Mobile Robot Navigation using Active Vision. PhD thesis, Oxford University, 1998.
No context found.
A. J. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1998.
No context found.
A. J. Davison, "Mobile Robot Navigation Using Active Vision" PhD Dissertation, Robotics Research Group, University of Oxford, 1999.
No context found.
A. J. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1998.
No context found.
A. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, University of Oxford, 1988.
No context found.
A.J. Davison. Mobile Robot Navigation Using Active Vision. PhD thesis, Department of Engineering Science, University of Oxford, 1998.
No context found.
A. J. Davison, "Mobile Robot Navigation Using Active Vision" PhD Dissertation, Robotics Research Group, University of Oxford, 1999.
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