Assessing geometry perception of direct time-of-flight sensors for robotic safety

Gimpelj, Jakob (author), Munih, Marko (author)

Time-of-flight sensors have emerged as a viable solution for real-time distance sensing in robotic safety applications due to their compact size, fast response, and contactless operation. This study addresses one of the key challenges with time-of-flight sensors, focusing on how they perceive and evaluate the environment, particularly in the presence of complex geometries and reflective surfaces. Using a Universal Robots UR5e arm in a controlled indoor workspace, two different sensors were tested across eight scenarios involving objects of varying shapes, sizes, materials, and reflectivity. Quantitative metrics including the root mean square error, mean absolute error, area difference, and others were used to evaluate measurement accuracy. Results show that the sensor’s field of view and operating principle significantly affect its spatial resolution and object boundary detection, with narrower fields of view providing more precise measurements and wider fields of view demonstrating greater resilience to specular reflections. These findings offer valuable insights into selecting appropriate ToF sensors for integration into robotic safety systems, particularly in environments with reflective surfaces and complex geometries.

• Language: English
• Keywords: direct ToF, reflectivity, robotic safety, sensor evaluation metrics, sensor field of view, shape detection, single-point ToF, surface material effects, time-of-flight sensor
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2025
• Number of pages: 19 str.
• Numbering: Vol. 25, issue 14, art. 4385
• PID: 20.500.12556/RUL-171148
• UDC: 007.52
• ISSN on article: 1424-8220
• DOI: 10.3390/s25144385
• COBISS.SI-ID: 245338115
• Publication date in RUL: 11.08.2025

Record is a part of a journal

• Title: Sensors
• Shortened title: Sensors
• Publisher: MDPI
• ISSN: 1424-8220
• COBISS.SI-ID: 10176278

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: neposredni ToF, odbojnost, varnost robotov, merila za ocenjevanje senzorjev, vidno polje senzorja, zaznavanje oblike, enotočkovni ToF, vplivi materiala površine, senzor časa leta