Efficient Calibration of Agent-Based Traffic Simulation Using Variational Auto-Encoder | |
Peijun Ye2; Fenghua Zhu2; Yisheng Lv2; Xiao Wang1; Yuanyuan Chen2 | |
2022-11 | |
会议日期 | Oct. 08-12, 2022 |
会议地点 | Macau, China |
关键词 | Agent-Based Model Calibration |
卷号 | 无 |
期号 | 无 |
DOI | 10.1109/ITSC55140.2022.9922234 |
页码 | 3077-3082 |
英文摘要 | In agent-based traffic simulation, calibration is an essential stage before the models applied to reproduce the individual/group travel behaviors. While traditional methods suffer from a high computational complexity, this paper proposes an improved method to alleviate the computational burden for large-scaled simulations. Specifically, we introduce variational auto-encoder to compress the original agent state vector into a lower dimensional hidden space, where the state transfer probability is calculated fast. Then the probability is mapped into the original space through a decoder, to achieve the agent travel parameters. The dynamic calibration method is tested with other baselines in urban travel demand analysis. Experiment results demonstrate that our method brings about 19% elevation of efficiency with the same accuracy of calibration. |
源文献作者 | IEEE |
会议录 | 无
![]() |
会议录出版者 | IEEE |
会议录出版地 | Macau, China |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57123] ![]() |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
通讯作者 | Peijun Ye |
作者单位 | 1.Qingdao Academy of Intelligent Industries 2.Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Peijun Ye,Fenghua Zhu,Yisheng Lv,et al. Efficient Calibration of Agent-Based Traffic Simulation Using Variational Auto-Encoder[C]. 见:. Macau, China. Oct. 08-12, 2022. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论