Estimation of Pedestrian Context based on Interaction of circulation with active real environment

2017 Fiscal Year Final Research Report

• Project/Area Number: 26330295
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Intelligent robotics
• Research Institution: The University of Tokyo
• Principal Investigator: Wakuda Yuki 東京大学, 大学院情報学環, 特任助教 (00377847)
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: 学習 / 概念獲得 / コンテキストアウェア / モデリング / 測位 / ナビゲーション

Outline of Final Research Achievements

In this research, we call human's situation and actions as Context, and with regard to the movement of pedestrians as a subject, This research tackled human' s Context estimation. Based on the sensor data that observed human motion (walking, stair climbing up and down, forward traveling, overtaking of obstacles), It is estimated each of these motions and estimate the chain of information indicating human behavior as Context. With respect to the proposed method, experiments have been conducted by using experimental data on data obtained from 1-kHz sampling of 3-axis acceleration, triaxial angular velocity, triaxial geomagnetism, and pressure data for human motion. Moreover, by modeling the transition of Context, this research built a model that estimates the next action and the Intention of the person who estimates the direction and destination of movement.

Free Research Field

ユビキタスコンピューティング