| Автор | Jakobi, Nick |
| Дата выпуска | 1997 |
| dc.description | For several years now, various researchers have endeavored to apply artificial evolution to the automatic design of control systems for real robots. One of the major challenges they face concerns the question of how to assess the fitness of evolving controllers when each evolutionary run typically involves hundreds of thousands of such assessments. This article outlines new ways of thinking about and building simulations upon which such assessments can be performed. It puts forward sufficient conditions for the successful transfer of evolved controllers from simulation to reality and develops a potential methodology for building simulations in which evolving controllers are forced to satisfy these conditions if they are to be reliably fit. It is hypothesized that as long as simulations are built according to this methodology, it does not matter how inaccurate or incomplete they are: Controllers that have evolved to be reliably fit in simulation still will transfer into reality. Two sets of experiments are reported, both of which involve minimal look-up table-based simulations built according to these guidelines. In the first set, controllers were evolved that allowed a Khepera robot to perform a simple memory task in the real world. In the second set, controllers were evolved for the Sussex University gantry robot that were able to distinguish visually a triangle from a square, under extremely noisy real-world conditions, and to steer the robot toward the triangle. In both cases, controllers that were reliably fit in simulation displayed extremely robust behavior when downloaded into reality. |
| Издатель | Sage Publications |
| Тема | simulations |
| Тема | evolutionary robotics |
| Тема | robot-environment interactions; neural networks |
| Название | Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis |
| Тип | Journal Article |
| DOI | 10.1177/105971239700600205 |
| Print ISSN | 1059-7123 |
| Журнал | Adaptive Behavior |
| Том | 6 |
| Первая страница | 325 |
| Последняя страница | 368 |
| Аффилиация | Jakobi, Nick, University of Sussex |
| Выпуск | 2 |
| Библиографическая ссылка | Beer, R., & Gallagher, J. (1992). Evolving dynamic neural networks for adaptive behavior. Adaptive Behavior, 1, 91-122. |
| Библиографическая ссылка | Braitenberg, V. (1984). Vehicles: Experiments in synthetic psychology . Cambridge, MA: MIT Press/ Bradford Books. |
| Библиографическая ссылка | Brogan, W.L. (1991). Modern control theory (3rd ed.). New York: Prentice Hall . |
| Библиографическая ссылка | Brooks, R. (1991). Intelligence without reason. In Proceedings of the Twelfth International Joint Conference on Artificial Intelligence San Mateo, CA: Morgan Kauffman. |
| Библиографическая ссылка | Chiel, H., Beer, R., Quinn, R., & Espenschied, K. (1992). Robustness of a distributed neural network controller for locomotion in a hexapod robot. IEEE Transactions on Robotics and Automation, 8(3), 293-303. |
| Библиографическая ссылка | Collett, T.S. (1996). Insect navigation en-route to the goal: Multiple strategies for the use of landmarks. Journal of Experimental Biology, 199(1), 227-235. |
| Библиографическая ссылка | Collins, R., &Jefferson, D. (1991). Selection in massively parallel genetic algorithms . In R. K. Belew & L. B. Booker (Eds.), Proceedings of the Fourth International Conference on Genetic Algorithms, ICGA-91. San Mateo, CA: Morgan Kaufmann. |
| Библиографическая ссылка | Floreano, D., & Mondada, F. (1994). Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In D. Cliff, P. Husbands, J. Meyer, & S. Wilson (Eds.), From animals to animats 3: Proceedings of the Third International Conference on the Simulation of Adaptive Behavior , Vol. 3. Cambridge, MA: MIT Press/Bradford Books. |
| Библиографическая ссылка | Harvey, I. (1992). Species adaptation genetic algorithms: The basis for a continuing saga. In E J. Varela & P. Bourgine (Eds.), Toward a practice of autonomous systems: Proceedings of the First European Conference on Artificial Life. Cambridge, MA: MIT Press/Bradford Books. |
| Библиографическая ссылка | Harvey, I., Husbands, P., & Cliff, D. (1994). Seeing the light: Artificial evolution, real vision . In D. Cliff, P Husbands, J. Meyer, & S. Wilson (Eds.), From animals to animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behavior, Vol. 3. Cambridge, MA: MIT Press/Bradford Books. |
| Библиографическая ссылка | Horridge, G. (1992). What can engineers learn from insect vision. Philosophical Transactions of the Royal Society of London, 337(1281), 271-282. |
| Библиографическая ссылка | Husbands, P., & Harvey, I. (1992). Evolution versus design: Controlling autonomous robots. In Integrating perception, planning and action: Proceedings of the Third Annual Conference on Artificial Intelligence, Simulation and Planning Los Alamitos, CA: IEEE Press. |
| Библиографическая ссылка | Husbands, P., Harvey, I., & Cliff, D. (1993). An evolutionary approach to situated a.i. In A. Sloman, D. Hogg, G. Humphreys, A. Ramsay, & D. Partridge (Eds.), Prospects for artificial intelligence. Amsterdam: IOS Press. |
| Библиографическая ссылка | Husbands, P., Harvey, I., Jakobi, N., Thompson, A., & Cliff, D. (1997). A case study in evolutionary robotics. In T. Back, D. Fogel, & Z. Michalewicz (Eds.), Handbook of evolutionary computation. New York: Oxford University. |
| Библиографическая ссылка | Jakobi, N. (1996). Encoding scheme issues for open-ended artificial evolution. In H.-M. Voigt, W Ebeling, I. Rechenberg , & H.-P. Schwefel (Eds.), Proceedings of the Fourth International Conference on Parallel Problem Solving in Nature. Berlin: Springer-Verlag. |
| Библиографическая ссылка | Jakobi, N. (1997a). Half-baked, ad-hoc and noisy: Minimal simulations for evolutionary robotics. In P. Husbands & I. Harvey (Eds.), Proceedings of the Fourth European Conference on Artificial Life . Cambridge, MA: MIT Press. |
| Библиографическая ссылка | Jakobi, N. (1997b). A minimal simulation for evolving walking behaviour in an octopod robot. Cognitive science research paper CSRP464, University of Sussex. |
| Библиографическая ссылка | Jakobi, N., Husbands, P., & Harvey, I. (1995). Noise and the reality gap: The use of simulation in evolutionary robotics. In E Moran, A. Moreno, J. Merelo, & P. Chacon (Eds.), Advances in artificial life: Proceedings of the Third European Conference on Artificial Life. Berlin: Springer-Verlag. |
| Библиографическая ссылка | K-Team (1993). Khepera user's manual. Lausanne: EPFL. |
| Библиографическая ссылка | Matarić, M., & Cliff, D. (1996). Challenges in evolving controllers for physical robots. Robot and Autonomous Systems, 19(1), 67-83. |
| Библиографическая ссылка | Michel, O. (1995). An artificial life approach for the synthesis of autonomous agents. In J. Alliot, E. Lutton, E. Ronald, M. Schoenauer, & D. Snyers (Eds.), Proceedings of the European Conference on Artificial Evolution. Berlin: Springer-Verlag. |
| Библиографическая ссылка | Miglino, O., Lund, H., & Nolfi, S. (1995). Evolving mobile robots in simulated and real environments . Artificial Life, 2(4), 417-434. |
| Библиографическая ссылка | Nilsson, N.J. (1984). Shakey the robot (Tech. Note 323). Menlo Park, CA: SRI International. |
| Библиографическая ссылка | Nolfi, S., Floreano, D., Miglino, O., & Mondada, E. (1994a). How to evolve autonomous robots: Different approaches in evolutionary robotics (Tech. Rep. PCIA-94-03). Rome , Italy: Department of Cognitive Processes and Artificial Intelligence. |
| Библиографическая ссылка | Nolfi, S., Miglino, O., & Parisi, D. (1994b). Phenotypic plasticity in evolving neural networks . In P Gaussier & J.-D. Nicoud (Eds.), Proceedings of the "From Perception to Action" Conference. Cambridge, MA: IEEE Computer Society Press. |
| Библиографическая ссылка | Thompson, A. (1995). Evolving electronic robot controllers that exploit hardware resources. In F. Moran, A. Moreno, J. Merelo, & P. Chacon (Eds.), Advances in artificial life: Proceedings of the Third European Conference on Artificial Life. (Lecture Notes in Artificial Intelligence 929.) Berlin: Springer-Verlag. |
| Библиографическая ссылка | Thompson, A. (1996). An evolved circuit, intrinsic in silicon, entwined with physics. In T. Higuchi & M. Iwata (Eds.), Proceedings of the First International Conference on Evolvable Systems (ICES'96), LNCS. Berlin: Springer-Verlag. |
| Библиографическая ссылка | Wehner, R. (1987). Matched—filters—neural models of the external world. Journal of Comparative Physiology, 161(4), 551-531. |
