Construction of behavioral decision mechanism based on prediction of perceptual information for elucidation of environmental adaptability

2023 Fiscal Year Final Research Report

• Project/Area Number: 22K20432
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 0302:Electrical and electronic engineering and related fields
• Research Institution: Osaka Metropolitan University
• Principal Investigator: KANATA Sayaka 大阪公立大学, 大学院工学研究科, 講師 (60605567)
• Project Period (FY): 2022-08-31 – 2024-03-31
• Keywords: 自律移動 / 環境適応 / 階層化システム

Outline of Final Research Achievements

The aim of this research project is to elucidate the robot's ability to adapt to its environment in order to realize a robot that can achieve its work objectives in an unknown environment. Focusing on the fact that living organisms have developed the brain, body structure, and sensory organs simultaneously, we decided to construct a mechanism to autonomously select appropriate actions by specifying the target state with the robot's sensory information. Focusing on the interaction between the environment and the robot's actions, this study examines a framework for processing a series of actions selected by the robot, the resulting changes in the environment, and how the robot perceives these changes to verify their practicality.

Free Research Field

制御工学

Academic Significance and Societal Importance of the Research Achievements

未知環境で働くロボットを実現するために，目標値をロボットの知覚情報として与える点が本研究の特徴である．知覚情報の予測が正確であることは，認識した環境とそのときの行動が期待通りであることを表す．予測のズレ要因を，行動の不確かさか環境推定の不確かさと分離せず，知覚情報の予測モデルを常に更新させ，とるべき行動の変容に結びつける．このことで，環境の不確かさと作業目的の両方を同時に議論するものである．行動計画の不確かさを定量化し，目標状態への距離と照らし合わせた行動システムを構築することで，環境の不確かさ低減と目標達成行動を結びつける枠組みを構築を目指した点が，本研究の特徴である．