建設ロボット

[VI-207] Application of deep reinforcement learning to bulldozer spreading work for the purpose of improving work efficiency and safety

〇DAISUKE TAJIMA¹, Daichi Noborio², Voot Tangkaratt³, Kenichi Hamamoto¹, Tadashi Oguma¹, Iduru Kuronuma¹, Satoru Miura¹, Toshihiro Kawashima², Kazuhiko Hayashi² (1.KAJIMA CORPORATION, 2.Komatsu Ltd., 3.Institute of Physical and Chemical Research)

Keywords:automated construction machine, bulldozer, spreading work, deep reinforcement learning, simulator, AI