God save the red queen! Competition in co-evolutionary robotics Export

@inproceedings{citeulike:3083474, abstract = {diwww.epfl.ch/lami/team/floreano / kant.irmkant.rm.cnr.it/nolfi.html In the simplest scenario of two coevolving populations in competition with each other, fitness progress is achieved at disadvantage of the other population\&\#039;s fitness. The everchanging fitness landscape caused by the competing species (named the \"Red Queen effect\") makes the system dynamics more complex, but it also provides a set of advantages with respect to single-population evolution. Here we present results from an experiment with two mobile robots, a predator equipped with vision and a much faster prey with simpler sensors. Without any effort in fitness design, a set of interesting behaviors emerged in relatively short time, such as obstacle avoidance, straight navigation, visual tracking, object discrimination (robot vs. wall), object following, and others. Although such experiments cannot yet be performed in real-time on populations of robots for technical reasons, the approach seems promising. 1 Competitive Co-Evolution Competitive co-evolution has recently attracted considerable interest in the community of Artificial Life and Evolutionary Computation. In the simplest scenario of two co-evolving populations, fitness progress is achieved at disadvantage of the other population\&\#039;s fitness. Although it is easy to point out several examples of such situation in nature (e.g., competition for limited food resources, host-parasite, predator-prey), it is more difficult to analyze and understand the importance and long-term effects of such \"arms races \" on the development of specific genetic traits and behaviors. An interesting complication is given by the \"Red Queen effect\"}, author = {Floreano, Dario and Nolfi, Stefano}, booktitle = {Genetic Programming 1997: Proceedings of the Second Annual Conference}, citeulike-article-id = {3083474}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.47.4797}, keywords = {coevolution, predator, robotics, steering, vision}, pages = {398--406}, posted-at = {2008-08-24 16:59:16}, priority = {2}, title = {God save the red queen! Competition in co-evolutionary robotics}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.47.4797}, volume = {5}, year = {1997} }

TY - CONF ID - citeulike:3083474 L3 - citeulike-article-id:3083474 N2 - diwww.epfl.ch/lami/team/floreano / kant.irmkant.rm.cnr.it/nolfi.html In the simplest scenario of two coevolving populations in competition with each other, fitness progress is achieved at disadvantage of the other population's fitness. The everchanging fitness landscape caused by the competing species (named the "Red Queen effect") makes the system dynamics more complex, but it also provides a set of advantages with respect to single-population evolution. Here we present results from an experiment with two mobile robots, a predator equipped with vision and a much faster prey with simpler sensors. Without any effort in fitness design, a set of interesting behaviors emerged in relatively short time, such as obstacle avoidance, straight navigation, visual tracking, object discrimination (robot vs. wall), object following, and others. Although such experiments cannot yet be performed in real-time on populations of robots for technical reasons, the approach seems promising. 1 Competitive Co-Evolution Competitive co-evolution has recently attracted considerable interest in the community of Artificial Life and Evolutionary Computation. In the simplest scenario of two co-evolving populations, fitness progress is achieved at disadvantage of the other population's fitness. Although it is easy to point out several examples of such situation in nature (e.g., competition for limited food resources, host-parasite, predator-prey), it is more difficult to analyze and understand the importance and long-term effects of such "arms races " on the development of specific genetic traits and behaviors. An interesting complication is given by the "Red Queen effect" EP - 406 TI - God save the red queen! Competition in co-evolutionary robotics VL - 5 T2 - Genetic Programming 1997: Proceedings of the Second Annual Conference SP - 398 KW - coevolution KW - predator KW - robotics KW - steering KW - vision AU - Floreano, Dario AU - Nolfi, Stefano PY - 1997/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.47.4797 ER -