| Presentation | 2018-11-05 [Poster Presentation] Crowd Navigation via Bayesian Optimization of Multi-agent Simulation Hitoshi Shimizu, Takuma Otsuka, Tomoharu Iwata, Hiroshi Sawada, Futoshi Naya, Naonori Ueda, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In a large event where a large number of people gather, to prepare plans for safely guiding visitors in advance, prediction and evaluation of guidance plans have been carried out using a crowd simulator. However, when there are many patterns of crowd guidance plans, there is a problem that simulation takes a lot of calculation time. Therefore, it is important to develop a method to efficiently obtain the optimal solution. In this paper, we propose a method to search guidance plans as close to optimal as possible by merely executing a simulation of a few patterns using Bayesian optimization rather than exhaustively searching. We applied the proposed method to pseudo-human flow data and evaluated on a simulator. Simulation evaluation showed that the proposed method can search guidance measures more efficiently than random search. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | |
| Paper # | IBISML2018-57 |
| Date of Issue | 2018-10-29 (IBISML) |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2018/11/5(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Hokkaido Citizens Activites Center (Kaderu 2.7) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Information-Based Induction Science Workshop (IBIS2018) |
| Chair | Hisashi Kashima(Kyoto Univ.) |
| Vice Chair | Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST) |
| Assistant | Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Poster Presentation] Crowd Navigation via Bayesian Optimization of Multi-agent Simulation |
| Sub Title (in English) | |
| Keyword(1) | |
| Keyword(2) | |
| Keyword(3) | |
| 1st Author's Name | Hitoshi Shimizu |
| 1st Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 2nd Author's Name | Takuma Otsuka |
| 2nd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 3rd Author's Name | Tomoharu Iwata |
| 3rd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 4th Author's Name | Hiroshi Sawada |
| 4th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 5th Author's Name | Futoshi Naya |
| 5th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 6th Author's Name | Naonori Ueda |
| 6th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| Date | 2018-11-05 |
| Paper # | IBISML2018-57 |
| Volume (vol) | vol.118 |
| Number (no) | IBISML-284 |
| Page | pp.pp.99-104(IBISML), |
| #Pages | 6 |
| Date of Issue | 2018-10-29 (IBISML) |