日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

共有制御/ヒューマンマシンインタフェースarXiv:2009.04100

前腕表面筋電位を用いた適応型ドライバー・自動化共有ステアリング制御

Adaptive driver-automation shared steering control via forearm surface electromyography measurement

シェア:XThreadsFacebookLINEはてブBluesky

ドライバーの前腕の表面筋電位から握力を推定し、ハプティックガイダンスの権限を適応的に変化させる共有ステアリング制御を設計し、二重車線変更タスクで運転行動とワークロードへの効果を評価した。

著者: Zheng Wang, Satoshi Suga, Edric John Cruz Nacpil, Zhanhong Yan, Kimihiko Nakano

分類: cs.HC, cs.RO, cs.SY, eess.SY

原文アブストラクト

Shared steering control has been developed to reduce driver workload while keeping the driver in the control loop. A driver could integrate visual sensory information from the road ahead and haptic sensory information from the steering wheel to achieve better driving performance. Previous studies suggest that, compared with adaptive automation authority, fixed automation authority is not always appropriate with respect to human factors. This paper focuses on designing an adaptive shared steering control system via sEMG (surface electromyography) measurement from the forearm of the driver, and evaluates the effect of the system on driver behavior during a double lane change task. The shared steering control was achieved through a haptic guidance system which provided active assistance torque on the steering wheel. Ten subjects participated in a high-fidelity driving simulator experiment. Two types of adaptive algorithms were investigated: haptic guidance decreases when driver grip strength increases (HG-Decrease), and haptic guidance increases when driver grip strength increases (HG-Increase). These two algorithms were compared to manual driving and two levels of fixed authority haptic guidance, for a total of five experimental conditions. Evaluation of the driving systems was based on two sets of dependent variables: objective measures of driver behavior and subjective measures of driver workload. The results indicate that the adaptive authority of HG-Decrease yielded lower driver workload and reduced the lane departure risk compared to manual driving and fixed authority haptic guidance.

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI