Dynamic Flies: Using Real-Time Parisian Evolution in Robotics
The Fly algorithm is a Parisian evolution strategy devised for parameter space exploration in computer vision applications, which has been applied to stereovision. The resulting scene model is a set of 3-D points which concentrate upon the surfaces of obstacles. In this paper, we present how the evolutionary scene analysis can be continuously updated and integrated into a specific real-time mobile robot navigation system. Simulation-based experimental results are presented.
KeywordsMobile Robot Obstacle Avoidance Robot Navigation Robot Simulator Dist Goal
Unable to display preview. Download preview PDF.
- 1.J. Louchet. Using an individual evolution strategy for stereovision. Genetic Programming and Evolvable Machines. Kluwer, to appear, 2001.Google Scholar
- 2.P. Collet, E. Lutton, F. Raynal, and M. Schoenauer. Individual GP: an alternative viewpoint for the resolution of complex problems. In Genetic and Evolutionary Computation Conference GECCO99. Morgan Kaufmann, San Francisco, CA, 1999.Google Scholar
- 3.R.M. Haralick. Using perspective transformations in scene analysis. Computer Graphics and Image Processing, (13):191–221, 1980.Google Scholar
- 4.R.C. Jain, R. Kasturi, and B.G. Schunck. Machine Vision. McGraw-Hill, New York, 1994.Google Scholar
- 5.R. Salomon and P. Eggenberger. Adaptation on the evolutionary time scale: a working hypothesis and basic experiments. In Springer Lecture Notes on Computer Science, number 1363, pages 251–262. Springer-Verlag, Berlin, 1997.Google Scholar
- 7.I. Ulrich and J. Borenstein. Vfh+: Reliable obstacle avoidance for fast mobile robots. In Procedings of the IEEE Conference On Robotics and Automation, ICRA’98, pages 1572–1577, Leuven, Belgium, May 1998.Google Scholar
- 8.J. Van Dam and B. Krose F. Groen. Transforming occupancy grids under robot motion. In S. Gielen and B. Kappe, editors, Artificial neural networks, page 318. Springer-Verlag, 1993.Google Scholar
- 9.M.C. Martin and H.P. Moravec. Robots evidence grid. Technical report, The Robotics Institute, Carnegie Mellon University, March 1996.Google Scholar
- 10.Y. Koren and J. Borenstein. Potentialfield methodes and their inherent limitations for mobile robot navigation. In Procedings of the IEEE Conference On Robotics and Automation, ICRA’91, pages 1398–1404, Sacramento, California, April 7-12 1991.Google Scholar
- 11.John S. Zelek. Complete real-time path planning during sensor-based discovery. In IEEE/RSJ International Conference on Intelligent Robots and systems, 1998.Google Scholar
- 12.B.H. Krogh. A generalized potential field approach to obstacle avoidance control. Robotics Research, August 1984.Google Scholar
- 14.R.A. Brooks and J.H. Connel. Asynchronous distributed control system for a mobile robot. In SPIE86Cambridge Symposium on Optical and Optoelectronic Engineering, Cambridge, MA, pages 77–84, October 1986.Google Scholar
- 15.cumuli project: Computational understanding of multiple images, http://www.inrialpes.fr/cumuli.
- 16.I. Rechenberg. Evolution strategy. In J.M. Zurada, R.J. MarksII, and C.J. Robinson, editors, Computational Intelligence imitating life, pages 147–159. IEEE Press, Piscataway, NJ, 1994.Google Scholar
- 17.P.K. Ser, S. Clifford, T. Choy, and W.C. Siu. Genetic algorithm for the extraction of nonanalytic objects from multiple dimensional parameter space. Computer Vision and Image Understanding, vol. 73no. 1, Academic Press: Orlando, FL, pages 1–13, 1999.Google Scholar
- 18.E. Lutton and P. Martinez. A genetic algorithm for the detection of 2D geometric primitives in images. In The Proceedings of the International Conference on Pattern Recognition, ICPR’94, pages 526–528, Los Alamitos, CA, October 9-13 1994. IEEE Computer Society.Google Scholar