概要
This paper proposes an automatic construction technique of transferable loading algorithms based on Cartesian Genetic Programming. The proposed method aims to construct the loading algorithm with a few hundred fitness evaluations by optimizing the execution order of rules to decide a type of multiple cardboard boxes and their loadable positions simultaneously. Experimental results show that auto-constructed loading algorithms can derive competitive performances to defined baselines under two hundred fitness evaluations on similar problems without any additional fitness evaluation.
文献種別
収録
情報処理学会論文誌「数理モデル化と応用」, Vol. 14, No. 3, pp. 11–26
参考
- 本サイトの全ての添付ファイルは著者バージョンであり，出版バージョンと一致しない可能性があります．
- 本ジャーナルは，国内会議である第131回MPS研究会と連動して募集されました．
