A novel vision-based multi-functional sensor for normality and position measurements in precise robotic manufacturing

Mohamad Halwani, Abdulla Ayyad, Laith AbuAssi, Yusra Abdulrahman, Fahad Almaskari, Hany Hassanin, Abdulqader Abusafieh, Yahya Zweiri

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

Cobots play an essential role in the fourth industrial revolution and the automation of complex manufacturing processes. However, cobots still face challenges in achieving high precision, which obstructs their usage in precise applications such as the aerospace industry. Nonetheless, advances in perception systems unlock new cobot manufacturing capabilities. This paper presents a novel multi-functional sensor that combines visual and tactile feedback using a single optical sensor, featuring a moving gate mechanism. This work also marks the first integration of Vision-Based Tactile Sensing (VBTS) into a robotic machining end-effector. The sensor provides vision-based tactile perception capabilities for precise normality control and exteroceptive perception for robot localization and positioning. Its performance is experimentally demonstrated in a precise robotic deburring application, where the sensor achieves the high-precision requirements of the aerospace industry with a mean normality error of 0.13° and a mean positioning error of 0.2 mm. These results open a new paradigm for using vision-based sensing for precise robotic manufacturing, which surpasses conventional approaches in terms of precision, weight, size, and cost-effectiveness.

Original languageBritish English
Pages (from-to)367-381
Number of pages15
JournalPrecision Engineering
Volume88
DOIs
StatePublished - Jun 2024

Keywords

  • Multi-functional sensor
  • Precise manufacturing
  • Robot deburring
  • Vision-based tactile sensing

Fingerprint

Dive into the research topics of 'A novel vision-based multi-functional sensor for normality and position measurements in precise robotic manufacturing'. Together they form a unique fingerprint.

Cite this