2023 Fiscal Year Final Research Report
A pedestrian guidance method with user adaptation based on emotional data extracted from walking history toward secure and comfortable life
Project/Area Number |
20K12074
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 62020:Web informatics and service informatics-related
|
Research Institution | University of Tsukuba |
Principal Investigator |
|
Project Period (FY) |
2020-04-01 – 2024-03-31
|
Keywords | 歩行者ナビゲーション / 高齢者 / 個人適応 / 心情推定 / 高度道路交通システム |
Outline of Final Research Achievements |
To improve the quality of life (QOL) of elderly people, we aim to develop a pedestrian navigation system that considers their physical difficulties, sense of security, and preferences. The emotional responses to route factors such as slopes, crowds, sidewalks, and parks (the weight of avoidance or passage) vary greatly among individuals, necessitating the development of an estimation mechanism that can adapt to each user. Therefore, by conducting surveys and walking experiments regarding route factors, we devised a method to estimate each user's weights based on the walking history, such as route factors avoided or passed during walking, and walking speed when passing by the factors. By conducting pedestrian experiments, we confirmed the feasibility and usefulness of the proposed method as a central method for building the desired navigation system, and identified issues that need to be resolved in order to improve the system's capabilities and insights into how to resolve them.
|
Free Research Field |
認知システム工学
|
Academic Significance and Societal Importance of the Research Achievements |
経路要因に対する心情は個々の差が著しいことから、同一モデルを用いた推論には限界があり、高いユーザ満足度を得るには個人特化型ナビ(パーソナルナビ)が必要である。この実現手法は世界的に研究されているが、対象とする経路要因や重み推定手法の妥当性の検討不足、ユーザ属性が限定的など、ユーザの実状と乖離する可能性を有している。本研究では、ユーザ属性や歩行履歴を用いる自動調整機構を有する経路要因評価モデル群を提案し、多様性への適応を図った。この実現により実利用時にコストモデルが自動的に調整されることから、ユーザは評価過程を意識することなく、自分に適した経路サービスを受けることが可能となる。
|