座面圧力を用いた自動運転時のドライバ状態推定

書誌事項

タイトル別名
  • Driver state estimation during automatic driving using seat pressure

抄録

<p>Various driver states are predicted during autonomous driving. Therefore, it is necessary to present information that can flexibly respond to behavior during autonomous driving. At that time, driver state estimation technology becomes important. In this research, we focused on the seat pressure sheet that can acquire the information only by sitting down. we measured seat pressure distribution using a driving simulator, and predicted driving behavior using a convolutional neural network. In this research, we predicted five driver states: "Forward gaze", "Cell phone use", "Distract (right)", "Sleeping", and "Distract (left)”. As a result, it was possible to predict with an accuracy of 78.8% in inter participant evaluation and 97.3% in overall evaluation.</p>

収録刊行物

詳細情報 詳細情報について

問題の指摘

ページトップへ