Automated picking-sorting system for assembling components in an IKEA chair based on the robotic vision system

ABSTRACT

With the rapid growth of the furniture product line industry and IKEA as the one of the pioneers, manual labour (and its limits of stability and high cost) is increasingly being replaced by automated systems. This is particularly due to the explosion of artificial intelligence techniques, which are practically useful in assembling tasks, which is one of the most common processes in furniture production. Loading connecting components with a standard posture is a representative example of a technique that is necessary and mostly performed by humans at present. This paper mainly focuses on the development of an automaticity robot system that provides an accurate and robust system for picking and sorting connecting components with two robot arms combined with optimized socket designs to increase the success probability. The performance of the proposed picking-sorting robots has been validated with success rates of picking-and-sorting tests ranging from 91.8% to 98.7% for all types of objects and operation times from 17.5 s to 25 s.

KEYWORDS:

• Assembling lines
• computer vision
• neural network applications
• image processing

Acknowledgments

This research was financially supported by the Ministry of Trade, Industry, and Energy (MOTIE), Korea, under the “Digital Manufacturing Platform (DigiMaP)” (reference number N0002598) supervised by the Korea Institute for Advancement of Technology (KIAT).

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The author Prof. Jonghun Yoon received research funding from a National Research Foundation of Korea (NRF) , grant funded by the Korea Government Korean government (MSIT) (No. 2019R1A2C4070160).