Bin-Picking Solution for Randomly Placed Automotive Connectors Based on Machine Learning Techniques

Abstract

This paper presents the development of a bin-picking solution based on low-cost vision systems for the manipulation of automotive electrical connectors using machine learning techniques. The automotive sector has always been in a state of constant growth and change, which also implies constant challenges in the wire harnesses sector, and the emerging growth of electric cars is proof of this and represents a challenge for the industry. Traditionally, this sector is based on strong human work manufacturing and the need arises to make the digital transition, supported in the context of Industry 4.0, allowing the automation of processes and freeing operators for other activities with more added value. Depending on the car model and its feature packs, a connector can interface with a different number of wires, but the connector holes are the same. Holes not connected with wires need to be sealed, mainly to guarantee the tightness of the cable. Seals are inserted manually or, more recently, through robotic stations. Due to the huge variety of references and connector configurations, layout errors sometimes occur during seal insertion due to changed references or problems with the seal insertion machine. Consequently, faulty connectors are dumped into boxes, piling up different types of references. These connectors are not trash and need to be reused. This article proposes a bin-picking solution for classification, selection and separation, using a two-finger gripper, of these connectors for reuse in a new operation of removal and insertion of seals. Connectors are identified through a 3D vision system, consisting of an Intel RealSense camera for object depth information and the YOLOv5 algorithm for object classification. The advantage of this approach over other solutions is the ability to accurately detect and grasp small objects through a low-cost 3D camera even when the image resolution is low, benefiting from the power of machine learning algorithms.

Car Engines Comparative Analysis: Sustainable Approach

“…The adaptation of engines to the latest requirements is done through technological solutions [36], such as DOC (oxidation catalyst) and DPF (diesel particulate filter), among others. The requirements described in the European standard are revised systematically, which means regular work on new filters or additionally equipping the vehicle with a small supporting electric motor [35,37]. The introduction of further regulations also results in the reduction (downsizing) of engine capacities (reduction in the number of cylinders in internal combustion engines which are contemporary trends in downsizing) and in meeting national and European environmental standards [38,39].…”

Filtering Organized 3D Point Clouds for Bin Picking Applications

“…Thus, enhancing the quality of the data acquired and processed by a vision system is important. Different types of machine vision systems have been integrated with robotic arms for different bin-picking scenarios [8][9][10][11][12][13][14][15]. The choice of a particular system determines how the acquired data needs to be addressed by the post-processing algorithms.…”

Anthropomorphic Grasping of Complex-Shaped Objects Using Imitation Learning

“…However, with the widespread adoption of cooperative robots that can safely work in human environments, and the growing demand for small-quantity batch productions, we now see an increasing number of smart, flexible robotic manipulation systems used for many different tasks [1][2][3]. Furthermore, with recent advances in machine learning algorithms, with the help of low-cost, high-resolution depth sensors, now many robotic manipulation systems can perceive environments and manipulate objects utilizing sensory information to intelligently handle complex nonrepetitive tasks, such as bin picking [4,5].…”