Probabilistic Machine Learning for Task-Specific Autonomous Robots with Limited Data and Expert-Efficient Annotation

Research Project

Project/Area Number	25K17567
Research Category	Grant-in-Aid for Early-Career Scientists
Allocation Type	Multi-year Fund
Review Section	Basic Section 20020:Robotics and intelligent system-related
Research Institution	Utsunomiya University
Principal Investigator	MIYAGUSUKU・RIOS RENATO 宇都宮大学, 工学部, 准教授 (90845588)
Project Period (FY)	2025-04-01 – 2028-03-31
Project Status	Granted (Fiscal Year 2025)
Budget Amount *help	¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000) Fiscal Year 2027: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000) Fiscal Year 2026: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000) Fiscal Year 2025: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Keywords	確率的機械学習 / 自律移動ロボット / 選択的アノテーション
Outline of Research at the Start	This research proposes a novel framework using Probabilistic Machine Learning (PML) to enable autonomous robots deployment by developing task-specific ML models that can be trained with small datasets and minimize errors from input changes or unfamiliar data through established statistical methods.