EvaluationTechnology for Human Detection Performance of Non-contact Safety Sensors in Outdoor Environments

2021 Fiscal Year Final Research Report

• Project/Area Number: 19H02391
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 25020:Safety engineering-related
• Research Institution: National Institute of Advanced Industrial Science and Technology
• Principal Investigator: Sumi Yasushi 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (30357305)
• Co-Investigator(Kenkyū-buntansha): 金 奉根 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (10415672)
• Project Period (FY): 2019-04-01 – 2022-03-31
• Keywords: 機能安全 / 非接触安全センサ / 低視程環境 / ラボラトリテスト / 評価指標 / 国際標準化

Outline of Final Research Achievements

We proposed MOT (Minimum Object-detectable Transmittance) as a new sensor evaluation metric in low visibility environments. The paper summarizing the results was accepted in IEEE Sensors Journal and published with open access.
We improved the test apparatus for sensor evaluation. A system that automatically controls the spatial transmittance of simulated snowfall and a system that can record the trajectory of falling simulated snowflakes was constructed. A system to reproduce drizzle with a particle size of 0.5 mm or less was developed. A sensor evaluation software system was developed and published on github. A system was developed to estimate the visibility reduction caused by snowfall and fog using deep learning.

Free Research Field

ロボティクス

Academic Significance and Societal Importance of the Research Achievements

本研究は、降雨・降雪・霧などによる視程（見通しの悪さ）が非接触安全センサの検出性能に及ぼす影響を表す、新しい評価指標MOTを提案したものである。移動ロボットやドローン・自動運転車両等の実用化には、低視程環境下でも確実に動作する安全センサが必須になると予想されるので、今後、安全センサ製品の屋外における性能保証や試験方法、国際標準化が重要な意味を持つことになるだろう。