An evolutionary navigator for autonomous agents on unknown large-scale environments. Intelligent Automation and Soft Computing, 14(1):105-116, 2008. abstract bibtex Computation of a collision-free path for a movable object among obstacles is an important problem in the fields of robotics. In previous research we have introduced an evolutionary algorithm for a robot moving on a known map considering a 4-connected grid model, and we have obtained encouraging results. In this paper, we focus our attention on a more complex motion planning problem: An autonomous agent with a limited sensor capability which is moving in a completely unknown large-scale environment. We introduce an evolutionary approach that has shown some adaptation abilities due to its constant update of its environment knowledge, and re-planning only when it is strictly required. We compare our approach for various map sizes to a very well-known evolutionary algorithm and to the complete approach D* Lite. Our algorithm outperforms them in both CPU time and in the number of re-plannings. Copyright © 2008, TSI® Press.
@article{42949083342,
abstract = "Computation of a collision-free path for a movable object among obstacles is an important problem in the fields of robotics. In previous research we have introduced an evolutionary algorithm for a robot moving on a known map considering a 4-connected grid model, and we have obtained encouraging results. In this paper, we focus our attention on a more complex motion planning problem: An autonomous agent with a limited sensor capability which is moving in a completely unknown large-scale environment. We introduce an evolutionary approach that has shown some adaptation abilities due to its constant update of its environment knowledge, and re-planning only when it is strictly required. We compare our approach for various map sizes to a very well-known evolutionary algorithm and to the complete approach D* Lite. Our algorithm outperforms them in both CPU time and in the number of re-plannings. Copyright © 2008, TSI® Press.",
number = "1",
year = "2008",
title = "An evolutionary navigator for autonomous agents on unknown large-scale environments",
volume = "14",
pages = "105-116",
journal = "Intelligent Automation and Soft Computing"
}
Downloads: 0
{"_id":"PCXxxKNPtrZcKzs7w","bibbaseid":"anonymous-anevolutionarynavigatorforautonomousagentsonunknownlargescaleenvironments-2008","downloads":0,"creationDate":"2017-03-31T20:15:33.025Z","title":"An evolutionary navigator for autonomous agents on unknown large-scale environments","author_short":null,"year":2008,"bibtype":"article","biburl":"https://1fichier.com/?j9cpurkmnv","bibdata":{"bibtype":"article","type":"article","abstract":"Computation of a collision-free path for a movable object among obstacles is an important problem in the fields of robotics. In previous research we have introduced an evolutionary algorithm for a robot moving on a known map considering a 4-connected grid model, and we have obtained encouraging results. In this paper, we focus our attention on a more complex motion planning problem: An autonomous agent with a limited sensor capability which is moving in a completely unknown large-scale environment. We introduce an evolutionary approach that has shown some adaptation abilities due to its constant update of its environment knowledge, and re-planning only when it is strictly required. We compare our approach for various map sizes to a very well-known evolutionary algorithm and to the complete approach D* Lite. Our algorithm outperforms them in both CPU time and in the number of re-plannings. Copyright © 2008, TSI® Press.","number":"1","year":"2008","title":"An evolutionary navigator for autonomous agents on unknown large-scale environments","volume":"14","pages":"105-116","journal":"Intelligent Automation and Soft Computing","bibtex":"@article{42949083342,\n abstract = \"Computation of a collision-free path for a movable object among obstacles is an important problem in the fields of robotics. In previous research we have introduced an evolutionary algorithm for a robot moving on a known map considering a 4-connected grid model, and we have obtained encouraging results. In this paper, we focus our attention on a more complex motion planning problem: An autonomous agent with a limited sensor capability which is moving in a completely unknown large-scale environment. We introduce an evolutionary approach that has shown some adaptation abilities due to its constant update of its environment knowledge, and re-planning only when it is strictly required. We compare our approach for various map sizes to a very well-known evolutionary algorithm and to the complete approach D* Lite. Our algorithm outperforms them in both CPU time and in the number of re-plannings. Copyright © 2008, TSI® Press.\",\n number = \"1\",\n year = \"2008\",\n title = \"An evolutionary navigator for autonomous agents on unknown large-scale environments\",\n volume = \"14\",\n pages = \"105-116\",\n journal = \"Intelligent Automation and Soft Computing\"\n}\n\n","key":"42949083342","id":"42949083342","bibbaseid":"anonymous-anevolutionarynavigatorforautonomousagentsonunknownlargescaleenvironments-2008","urls":{},"downloads":0,"html":""},"search_terms":["evolutionary","navigator","autonomous","agents","unknown","large","scale","environments"],"keywords":[],"authorIDs":[],"dataSources":["gKiCRHjjC2iGthGEx"]}