Position Estimation for a Mobile Robot using Monocular Vision and Odometry
Estimation de la Position d'un Robot par Odométrie et Vision Monoculaire
OPEN ACCESS
We describe a localisation system for a robot moving in a known environment. Unlike the currently used methods for industrial robots, our approach does not require any beacons to be installed : the system uses odometry to estimate the vehicle position continuously, and corrects this estimation when necessary by identifying some objects of the environment through vision. These objects, used as landmarks, were previously recorded in a data base.
The different parts of the system are presented particularly the way the uncertainty on odometry is updated and how prior knowledge (position estimation and data base) is employed to facilitate landmark identification. 7 cm on xy and I deg on the heading is the typical precision obtained in term of localisation.
Résumé
Nous présentons un système de localisation pour un robot mobile évoluant dans un environnement connu. La méthode, contrairement à celles actuellement utilisées dans l'industrie, ne nécessite pas l'équipement du site en balises : la position du robot est estimée à chaque instant par odométrie, et recalée périodiquement en repérant, à l'aide d'une caméra mobile montée sur le véhicule, des objets de l'environnement jouant le rôle d'amer. Ces objets sont répertoriés dans une base de données constituée au préalable.
Les différentes composantes du système sont présentées : nous montrons en particulier comment l'incertitude sur la position du robot évolue avec les erreurs d'odométrie, et comment les connaissances a priori (position estimée, base de données) sont mises à profit pour identifier les amers . La précision typiquement obtenue en matière de localisation est de 7 cm selon xy et 1 deg en cap .
localisation, mobile robot, odometry, monocular vision, landmark.
Motsclés
localisation, robot mobile, odométrie, vision monoculaire, amer.
[1] N. Ayache, O. D. Faugeras, "Environment of a mobile robot", IEEE Trans. on Robotics and Automation, Vol. 5, No. 6, Dec. 1989.
[2] D. H. Ballard, C. M. Brown, "Computer Vision", Prentice-Hall, Englewood Cliffs, New Jersey, 1982.
[3] L. E. Banta, "Advanced dead reckoning navigation for mobile robots", PhD Thesis, Georgia Institute of Technology, Atlanta, 1987.
[4] Y Bar-Shalom, T.E. Fortmann, "Tracking and data association", Mathematics in Science and Engineering Series, Vol. 179, New York, Academic, 1988.
[5] M. Brady, H. Durant-Whyte, H. Hu, J. Leonard, P. Probert, B. S. Y. Rao, "Mobile robot research at the University of Oxford", Computing and Control Engineering Journal, Vol. 1, No 2, March 1990, pp 64-70.
[6] M. Buffa, "Navigation d'un Robot Mobile à l'aide de la Stéréovision et de la Triangulation de Delaunay", Thèse de I'Univ. de Nice, Nice, Juin 1993.
[7] R. Chatila, J. P. Laumond, "Position Referencing and Consistent World Modeling or Mobile Robot", In Proc. of the IEEE Int. Conf. on Robotics and Automation, 1985, pp 138-145.
[8] S. Y Chen, W. H. Tsai, "A systematic approach to analytic determination of camera parameters by line features", Pattern Recognition, Vol . 23, No. 8, 1990, pp 859-877.
[9] E Chenavier, J. L. Crowley, "Position Estimation for a Mobile Robot Using Vision and Odometry", In Proc. of the IEEE Conf. on Robotics and Automation, Nice, May 1992, Vol 3, pp 2588-2593.
[10] F. Chenavier, "Localisation d'un Robot Mobile par Odométrie et Vision Monoculaire", Thèse de l'Institut National Polytechnique de Grenoble, Grenoble, Sept. 1992.
[11] C. K. Cowan, P. D. Kovesi, "Automatic sensor placement from vision task requirements", IEEE Trans. on PAMI, Vol. 10, No. 3, May 1988, pp 407-416.
[12] I. J. Cox, "Blanche - An experiment in guidance and navigation of an autonomous robot vehicle", IEEE Trans. on Robotics and Automation, Vol. 7, No. 2, 1991, pp 193-204.
[13] J. L. Crowley, "World modeling and position estimation for a mobile robot using ultrasonic ranging", In Proc. of the IEEE Conf. on Robotics and Automation, Scottsdale, May 1989.
[14] J. L. Crowley, "Control of translation and rotation in a robot vehicle", In Proc. of the IEEE Conf. on Robotics and Automation, Scottsdale, May 1989.
[15] M. Dhome, M. Richetin, J. T. Lapresté, G. Rives, "Determination of the attitude of 3-D objects from a single perspective view", IEEE Trans . on PAMI, Vol. 11, No. 12, Dec. 1989, pp 1265-1278.
[16] M. Dhome, P. Reis, G. Rives, M. Richetin, C. Mersier, "Navigation par vision monoculaire d'un robot mobile dans un univers modélisé", Actes du Congrès AFCET INRIA Reconnaissance des Formes et Intelligence Artificielle, Lyon, Nov. 91, pp 449-454.
[17] H. E Durant-Whyte, "Uncertain geometry in robotics", IEEE Jounal on Robotics and Automation, Vol. 4, No. 1, 1988, pp 23-31.
[18] C. Durieu, "Algorithmes de localisation d'un robot mobile dans un milieu balisé par mesure de distances ou d'angle de gisement en tenant compte des mesures aberrantes. Algorithmes de calibration et recalage du champ de balises", Thèse à l'université de Paris XI, Paris, Fev. 1989.
[19] I. Fukui, "TV image processing to determine the position of a robot vehicle", Pattern Recognition 14, 1981, pp 101-109.
[20] W. D. Holcombe, S. L. Dickerson, J. W. Larsen, R. A. Bohlander, "Advanced in guidance systems for industrial automated guided vehicles", Proc. of the SPIE Vol. 1007, Mobile Robot III, Cambridge (USA), 1988, pp 288-296.
[21] R. Horaud, "New Method for Matching 3D Objects with Single Perspective View", IEEE Trans. on PAMI, Vol. 9, No. 3, May 1987, pp 401-412.
[22] J. Illingworth, J. Kittler, "A Survey of the Hough Transform", Computer Vision, Graphics, and Image Processing 44, 1988, pp 87-116.
[23] M. R. Kabuka, E. Arenas, "Position verification of a mobile robot using standart pattern", IEEE Journal on Robotics and Automation, Vol. RA-3, No. 6, Dec. 1987, pp 505-516.
[24] E. Krotkov, "Mobile robot localization using a single image", In Proc, of the IEEE Int. Conf. on Robotics and Automation, 1989, pp 978-983.
[25] K. D. Kuhnert, "Fusing dynamic vision and landmark navigation for autonomous driving", IEEE Int. Work. on Intelligent Robots and Systems IROS'90, 1990, pp 113-119.
[26] J. C. Lahaye, A. Chehikian, "Localisation d'Objets en Temps Réel par Transformée de Hough", Actes de la Semaine Internationale de l'Image Electronique, Nice, Avril 1986, pp 165-172.
[27] R. K. Lenz, R. Y. Tsai, "Techniques for Calibration of the Scale Factor and Image Center for High Accuracy 3-D Machine Vision Metrology", IEEE Trans. on PAMI, Vol. 10, No. 5, Sept. 1988, pp 713-720.
[28] J. Leonard, H. Durrant-Whyte, "Mobile robot localization by tracking geometric beacons", IEEE Trans. on Robotics and Automation, Vol. 7, No. 3, June 1991, pp 376-382.
[29] D. G. Lowe, "Three-dimensional object recognition from single twodimensional images", Artificial Intelligence 31, 1987, pp 355-395.
[30] Y T. Ren, S. P. Walker, "Position determination of automatically guided vehicles", The International Journal of Advanced Manufacturing Technology, Vol. 1, No 5, 1986, pp 45-53.
[31] R. C. Smith, P. Cheeseman, "On the Representation and Estimation of Spatial Uncertainty", The International Journal of Robotics Research, Vol. 5, No. 4, Winter 1986, pp 56-68.
[32] K. Sugihara, "Some location problems for robot navigation using single camera", Computer Vision, Graphics, and Image Processing 42,1988, pp 112129.
[33] H. Takeda, J. C. Latombe, "Sensory Uncertainty Field for Mobile Robot Navigation", In Proc. of the IEEE Conf. on Robotics and Automation, Nice, May 1992, pp 2465-2472.
[34] D. J. Torrieri, "Staticical theory of passive location systems", IEEE Trans . on Aerospace, and Electronic Systems, Vol. 20, No. 2, March 1984, pp 183-198.
[35] J. Vaganay, M. J. Aldon, "Sensor Integretion for Mobile Robot Localization", 24th International Symposium on Industrial Robots, Tokyo, Nov. 4-6, 1993.
[36] C. M. Wang, "Location Estimation and Uncertainty Analysis for Mobile Robot", In Proc, of the IEEE Int. Conf. on Robotics and Automation 88, Vol. 2, 1988, pp 1230-1235.