%0 Conference Paper %1 Nitschke:2008:gecco %A Nitschke, Geoff %A Schut, Martijn %B GECCO'08: Proc. 10th Genetic and Evolutionary Computation Conf. %C Atlanta, GA %D 2008 %E Keijzer, Maarten %E Antoniol, Giuliano %E Bates Congdon, Clare %E Deb, Kalyanmoy %E Doerr, Benjamin %E Hansen, Nikolaus %E Holmes, John H. %E Hornby, Gregory S. %E Howard, Daniel %E Kennedy, James %E Kumar, Sanjeev %E Lobo, Fernando G. %E Miller, Julian Francis %E Moore, Jason %E Neumann, Frank %E Pelikan, Martin %E Pollack, Jordan %E Sastry, Kumara %E Stanley, Kenneth %E Stoica, Adrian %E Talbi, El-Ghazali %E Wegener, Ingo %I ACM Press %K imported thesis %P 233--240 %R 10.1145/1389095.1389132 %T Designing Multi-Rover Emergent Specialization %X We compare the efficacy of the Enforced Sub-Populations (ESP) and Collective Neuro-Evolution (CONE) methods for designing behavioral specialization in a multi-rover collective behavior task. These methods are tested for Artificial Neural Network (ANN) controller design in an extension of the multi-rover task, where behavioral specialization is known to benefit task performance. The task is for multiple simulated autonomous vehicles (rovers) to maximize the detection of points of interest (red rocks) in a virtual environment. The task requires rovers to collectively sense such points of interest in order for them to be detected. Results indicate that the CONE method facilitates a level of specialization appropriate for achieving a significantly higher task performance, comparative to rover teams evolved by the ESP method. %@ 978-1-60558-130-9

@inproceedings{Nitschke:2008:gecco, abstract = {We compare the efficacy of the Enforced Sub-Populations (ESP) and Collective Neuro-Evolution (CONE) methods for designing behavioral specialization in a multi-rover collective behavior task. These methods are tested for Artificial Neural Network (ANN) controller design in an extension of the multi-rover task, where behavioral specialization is known to benefit task performance. The task is for multiple simulated autonomous vehicles (rovers) to maximize the detection of points of interest (red rocks) in a virtual environment. The task requires rovers to collectively sense such points of interest in order for them to be detected. Results indicate that the CONE method facilitates a level of specialization appropriate for achieving a significantly higher task performance, comparative to rover teams evolved by the ESP method.}, added-at = {2017-03-16T11:50:55.000+0100}, address = {Atlanta, GA}, author = {Nitschke, Geoff and Schut, Martijn}, biburl = {https://www.bibsonomy.org/bibtex/24d2b27303bcbf5938f58edfd568bbd1f/krevelen}, booktitle = {GECCO'08: Proc. 10th Genetic and Evolutionary Computation Conf.}, crossref = {gecco:2008}, doi = {10.1145/1389095.1389132}, editor = {Keijzer, Maarten and Antoniol, Giuliano and {Bates Congdon}, Clare and Deb, Kalyanmoy and Doerr, Benjamin and Hansen, Nikolaus and Holmes, John H. and Hornby, Gregory S. and Howard, Daniel and Kennedy, James and Kumar, Sanjeev and Lobo, Fernando G. and Miller, Julian Francis and Moore, Jason and Neumann, Frank and Pelikan, Martin and Pollack, Jordan and Sastry, Kumara and Stanley, Kenneth and Stoica, Adrian and Talbi, El-Ghazali and Wegener, Ingo}, interhash = {5c5163a973f6a397c24535cdc177c2ff}, intrahash = {4d2b27303bcbf5938f58edfd568bbd1f}, isbn = {978-1-60558-130-9}, keywords = {imported thesis}, owner = {Rick}, pages = {233--240}, publisher = {ACM Press}, publisher_address = {New York}, timestamp = {2017-03-16T11:54:14.000+0100}, title = {Designing Multi-Rover Emergent Specialization}, year = 2008 }