Article

Automatic design of vision-based obstacle avoidance controllers using genetic programming

Authors:

Antoine ManzaneraAuthors Info & Claims

EA'07: Proceedings of the Evolution artificielle, 8th international conference on Artificial evolution

Pages 25 - 36

Published: 29 October 2007 Publication History

Abstract

The work presented in this paper is part of the developmentof a robotic system able to learn context dependent visual clues to navigatein its environment. We focus on the obstacle avoidance problem asit is a necessary function for a mobile robot. As a first step, we use an offlineprocedure to automatically design algorithms adapted to the visualcontext. This procedure is based on genetic programming and the candidatealgorithms are evaluated in a simulation environment. The evolutionaryprocess selects meaningful visual primitives in the given contextand an adapted strategy to use them. The results show the emergenceof several different behaviors outperforming hand-designed controllers.

References

[1]

Santos-Victor, J., Sandini, G., Curotto, F., Garibaldi, S.: Divergent stereo for robotnavigation: learning from bees. In: IEEE Computer Society Conference on ComputerVision and Pattern Recognition, pp. 434-439 (1993).

[2]

Ebner, M., Zell, A.: Centering behavior with a mobile robot using monocularfoveated vision. Robotics and Autonomous Systems 32(4), 207-218 (2000).

[3]

Muratet, L., Doncieux, S., Brière, Y., Meyer, J.A.: A contribution to vision-based autonomous helicopter flight in urban environments. Robotics and AutonomousSystems 50(4), 195-209 (2005).

[4]

Hrabar, S.: Vision-Based 3D Navigation for an Autonomous Helicopter. PhD thesis,University of Southern California (2006).

[5]

Michels, J., Saxena, A., Ng, A.: High speed obstacle avoidance using monocularvision and reinforcement learning. In: Proceedings of the 22nd international conferenceon Machine learning, pp. 593-600 (2005).

Digital Library

[6]

Horswill, I.: Polly: A vision-based artificial agent. In: Proceedings of the EleventhNational Conference on Artificial Intelligence (AAAI-1993), pp. 824-829 (1993).

[7]

Lorigo, L., Brooks, R., Grimson, W.: Visually-guided obstacle avoidance in unstructuredenvironments. In: Proceedings of the 1997 IEEE/RSJ International Conferenceon Intelligent Robots and Systems, vol. 1, pp. 373-379 (1997).

[8]

Ulrich, I., Nourbakhsh, I.: Appearance-based obstacle detection with monocularcolor vision. In: Proceedings of AAAI Conference, pp. 866-871 (2000).

Digital Library

[9]

Harvey, I., Husbands, P., Cliff, D.: Seeing the Light: Artificial Evolution, RealVision. In: From Animals to Animats 3: Proceedings of the Third InternationalConference on Simulation of Adaptive Behavior, pp. 392-401 (1994).

Digital Library

[10]

Marocco, D., Floreano, D.: Active vision and feature selection in evolutionary behavioralsystems. From Animals to Animats 7, 247-255 (2002).

Digital Library

[11]

Mataric, M., Cliff, D.: Challenges in evolving controllers for physical robots.Robotics and Autonomous Systems 19(1), 67-83 (1996).

[12]

Walker, J., Garrett, S., Wilson, M.: Evolving controllers for real robots: A surveyof the literature. Adaptive Behavior 11(3), 179-203 (2003).

[13]

Ebner, M., Zell, A.: Evolving a task specific image operator. In: Evolutionary imageanalysis, signal processing and telecommunications: First european workshop,evoiasp, pp. 74-89 (1999).

Digital Library

[14]

Trujillo, L., Olague, G.: Synthesis of interest point detectors through genetic programming.In: Proceedings of the 8th annual conference on Genetic and evolutionarycomputation, pp. 887-894 (2006).

Digital Library

[15]

Ebner, M., Zell, A.: Evolving a behavior-based control architecture-From simulationsto the real world. In: Proceedings of Genetic and Evolutionary ComputationConference, vol. 2, pp. 1009-1014 (1999).

[16]

Pauplin, O., Louchet, J., Lutton, E., De La Fortelle, A.: Evolutionary Optimisationfor Obstacle Detection and Avoidance in Mobile Robotics. Journal of AdvancedComputational Intelligence and Intelligent Informatics 9(6), 622-629 (2005).

[17]

Olague, G., Puente, C.: Parisian evolution with honeybees for three-dimensional reconstruction. In: Proceedings of the 8th annual conference on Genetic and evolutionarycomputation, pp. 191-198 (2006).

Digital Library

[18]

Martin, M.: Evolving visual sonar: Depth from monocular images. Pattern RecognitionLetters 27(11), 1174-1180 (2006).

Digital Library

[19]

Barron, J., Fleet, D., Beauchemin, S.: Performance of optical flow techniques. InternationalJournal of Computer Vision 12(1), 43-77 (1994).

Digital Library

[20]

Koza, J.: Genetic Programming: On the Programming of Computers by NaturalSelection. MIT Press, Cambridge, MA, USA (1992).

Digital Library

[21]

Montana, D.: Strongly Typed Genetic Programming. Evolutionary Computation3(2), 199-230 (1995).

Digital Library

[22]

Whigham, P.: Grammatically-based genetic programming. In: Proceedings of theWorkshop on Genetic Programming: From Theory to Real-World Applications, pp.33-41 (1995).

[23]

Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjectivegenetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation6(2), 182-197 (2002).

Digital Library

Cited By

Barate RManzanera A(2008)Evolving Vision Controllers with a Two-Phase Genetic Programming System Using ImitationProceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats10.1007/978-3-540-69134-1_8(73-82)Online publication date: 7-Jul-2008
https://dl.acm.org/doi/10.1007/978-3-540-69134-1_8

Automatic design of vision-based obstacle avoidance controllers using genetic programming
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks

Recommendations

Automatic Design of Vision-Based Obstacle Avoidance Controllers Using Genetic Programming
Artificial Evolution
Abstract
The work presented in this paper is part of the development of a robotic system able to learn context dependent visual clues to navigate in its environment. We focus on the obstacle avoidance problem as it is a necessary function for a mobile ...
A vision based system for goal-directed obstacle avoidance
RoboCup 2004

We present a complete system for obstacle avoidance for a mobile robot. It was used in the RoboCup 2003 obstacle avoidance challenge in the Sony Four Legged League. The system enables the robot to detect unknown obstacles and reliably avoid them while ...
Obstacle avoidance of a mobile robot using vision system and ultrasonic sensor
ICIC'07: Proceedings of the intelligent computing 3rd international conference on Advanced intelligent computing theories and applications

This paper proposes obstacle collision avoidance algorithm for a mobile robot. To navigate without colliding with obstacles the mobile robot uses both the vision system approach and edge detection approach using ultrasonic sensor. The vision system ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

EA'07: Proceedings of the Evolution artificielle, 8th international conference on Artificial evolution

October 2007

329 pages

ISBN:3540793046

Editors:
Nicolas Monmarché
Ecole Polytechnique de l'Université de Tours, Laboratoire d'Informatique, Tours, France
,
El-Ghazali Talbi
Université des Sciences et Technologies de Lille, Laboratoire d'Informatique Fondamentale de Lille, Villeneuve d'Ascq, France
,
Pierre Collet
Université Louis Pasteur, Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection, Strasbourg, France
,
Marc Schoenauer
INRIA Saclay, Île-de-France, LRI, Université de Paris-Sud, Orsay, France
,
Evelyne Lutton
INRIA Saclay, Île-de-France, Orsay, France

Sponsors

Université François Rabelais de Tours
Conseil Régional du Centre
Ville de Tours
INRIA: Institut Natl de Recherche en Info et en Automatique
Université de Tours

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 29 October 2007

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
2
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 03 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Barate RManzanera A(2008)Evolving Vision Controllers with a Two-Phase Genetic Programming System Using ImitationProceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats10.1007/978-3-540-69134-1_8(73-82)Online publication date: 7-Jul-2008
https://dl.acm.org/doi/10.1007/978-3-540-69134-1_8

View Options

View options

Figures

Tables

Media

View Table of Conten