講演抄録/キーワード |
講演名 |
2019-09-24 15:50
Reinforcement learning for pedestrian agent route planning and collision avoidance ○Trinh Thanh Trung・Masaomi Kimura(SIT) SSS2019-21 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
Pedestrian navigation plays a significant role in many traffic safety simulation systems. In microscopic pedestrian navigation, most models use the concept of “forces” applied to the pedestrian agents to replicate the navigation environment. While the approach could provide believable results in regular situations, it does not always resemble natural pedestrian navigation behaviour in many typical settings. In our research, we proposed a novel approach using reinforcement learning for simulation of pedestrian agent route planning and collision avoidance problem. The primary focus of this approach is using human perception of the environment and danger awareness of interferences. |
キーワード |
(和) |
/ / / / / / / |
(英) |
pedestrian / reinforcement learning / PPO / navigation / route planning / / / |
文献情報 |
信学技報, vol. 119, no. 210, SSS2019-21, pp. 17-22, 2019年9月. |
資料番号 |
SSS2019-21 |
発行日 |
2019-09-17 (SSS) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
SSS2019-21 |