{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/evolution-of-swarm-robotics-systems-with","title":"Evolution of Swarm Robotics Systems with Novelty Search","arxiv_id":"1304.3362","date":"2013-04-11","proceeding":null,"authors":["Jorge Gomes","Paulo Urbano","Anders Lyhne Christensen"],"abstract":"Novelty search is a recent artificial evolution technique that challenges\ntraditional evolutionary approaches. In novelty search, solutions are rewarded\nbased on their novelty, rather than their quality with respect to a predefined\nobjective. The lack of a predefined objective precludes premature convergence\ncaused by a deceptive fitness function. In this paper, we apply novelty search\ncombined with NEAT to the evolution of neural controllers for homogeneous\nswarms of robots. Our empirical study is conducted in simulation, and we use a\ncommon swarm robotics task - aggregation, and a more challenging task - sharing\nof an energy recharging station. Our results show that novelty search is\nunaffected by deception, is notably effective in bootstrapping the evolution,\ncan find solutions with lower complexity than fitness-based evolution, and can\nfind a broad diversity of solutions for the same task. Even in non-deceptive\nsetups, novelty search achieves solution qualities similar to those obtained in\ntraditional fitness-based evolution. Our study also encompasses variants of\nnovelty search that work in concert with fitness-based evolution to combine the\nexploratory character of novelty search with the exploitatory character of\nobjective-based evolution. We show that these variants can further improve the\nperformance of novelty search. Overall, our study shows that novelty search is\na promising alternative for the evolution of controllers for robotic swarms.","url_abs":"http://arxiv.org/abs/1304.3362v1","url_pdf":"http://arxiv.org/pdf/1304.3362v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"evolution-of-swarm-robotics-systems-with","repo_url":"https://github.com/jorgemcgomes/evosimbad","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}