Objective and Quantitative Assessment of Reproduction of Tactile Feeling

2023 Fiscal Year Final Research Report

• Project/Area Number: 20H02121
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 20020:Robotics and intelligent system-related
• Research Institution: Keio University
• Principal Investigator: MIKI NORIHISA 慶應義塾大学, 理工学部(矢上), 教授 (70383982)
• Co-Investigator(Kenkyū-buntansha): 石塚 裕己 大阪大学, 大学院基礎工学研究科, 助教 (40784418)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: 触覚 / 触覚ディスプレイ / 事象関連電位 / 皮膚変形 / 自然言語処理 / 機械学習

Outline of Final Research Achievements

This research aimed to develop the methodology to evaluate the replicated tactile sensation quantitatively and objectively. Since the oddball tasks of tactile stimuli involves errors in the trigger detection, the conventional summation averaging cancels out not only the noise but also the ERP. Compensation of the trigger mismatch and data augmentation are proposed by Miki’s group and are verified to be effective in accurate detection of ERP. Ishizuka’s group successfully simulated the response of tactile receptors by modeling the neurons and the skins. In addition, the tactile samples and the tactile displays were newly developed while natural language processing, machine learning, and generative AI were successfully incorporated into the tactile research.

Free Research Field

人間工学

Academic Significance and Societal Importance of the Research Achievements

本研究の学術的意義は、事象関連電位ならびに、皮膚変形・神経モデルを用いる触覚評価手法を構築した点である。本手法を用いることで、主観的かつ定性的な実験評価が可能となり、触覚モデルの理解、構築が容易になる。また、触覚実験を支援する触覚サンプルや触覚ディスプレイを開発するとともに、触覚研究の律速となる被験者実験を回避可能な、自然言語処理、機械学習、生成Aiを用いた新たな手法を提案した。触覚研究のブレイクスルーにつながることが期待される。