With precision and clear vision: robots work autonomously in wire harness manufacturing

This automation has the potential to bring production back to a high-wage country, as it reduces costs, improves quality, and lowers the carbon footprint.

The manufacture of wiring harnesses is one of the last major challenges in industrial automation. While robots have long been performing a wide range of tasks in many industries, the assembly of complex wiring harnesses has remained the domain of manual labour until now. The reasons for this lie in the nature of the task itself: cables are flexible, dimensionally unstable components that are difficult to handle.

That is why cable harnesses are still manufactured exclusively by hand. Cable harness manufacturing is a classic "migratory industry" that moves to countries with low labour costs because of this. However, with rising demands, the desire for greater resilience within supply chains, and the goal of bringing production back to high-wage countries, there is also a growing effort to automate this process.

Cellios, which emerged from the Fraunhofer Institute for Manufacturing Engineering and Automation (IPA) in Stuttgart and was founded in 2024, has developed a solution specifically for this purpose. The company specialises in the manufacture of robot-based automation systems for cable assembly. At the heart of its portfolio are modular robot cells that digitise and automate the manual cable assembly process. The project partner for the world's first fully automated cable harness is TE Connectivity.

"Previous solutions often covered only partial steps of cable processing, meaning that pre-assembled cables had to be further processed manually. The goal of the project with TE Connectivity was therefore to fully automate the entire process, right up to electrical testing," explains Dr. Frank Nagele, CTO at Cellios.

First fully integrated, fully automated wire harness

Achieving this requires overcoming numerous challenges. For example, the terminated cable ends, known as crimps, which are only a few millimeters wide, must be inserted into the corresponding connectors. The greatest challenge, however, is the cable itself. Because cables do not have a rigid shape, the position of the crimp in the gripper changes with every handling operation. To reliably guide the crimp into the tiny cavity of a connector, an accuracy of at least one-tenth of a millimetre is required.

"In addition to the technical issues, there are also complex process-related questions. After all, the objective is to automate a process that has been entirely manual. Components such as connectors, cable-processing machines, and so on are designed for use by humans, not robots. On top of that, there is an enormous variety of wire harness variants that we want to accommodate through the flexible design of our assembly cells," explains Dr. Nagele.

Cellios' answer to these challenges is a modular system. The company maps the various stages of wire harness assembly to different modules. The individual process steps include connector singulation, cable preparation, crimping, cable routing, producing splice connections with an ultrasonic welding device, taping, and finally end-of-line testing. The most difficult task to automate so far is routing followed by contact insertion. As described above, the robot has to insert crimps measuring only a few millimetres into the connectors.

Until now, this task has been performed exclusively by hand directly on the routing board and has required the operator to exercise the utmost concentration, visual acuity, and dexterity. In the newly developed robot cell, the robot moves the gripped component to a 2D camera. There, the position and orientation of the crimp are determined and sent to the robot as a correction for assembly. A second camera is used to measure the target position.

The robot can therefore reach its target position through precise corrective movements and reliably insert the crimp into the connector. The necessary sensitivity is achieved through force control and force monitoring: A force-torque sensor on the robot measures the forces during insertion and regulates them so that the crimp is inserted optimally. Machine vision ensures the required accuracy.

Giving robots sight

"Without precise 'vision', the robot would literally be blind and unable to make the necessary corrections reliably and independently," explains Dr. Nagele. To overcome these challenges, Cellios turned to machine vision.

Sensors alone were not sufficient to determine the exact position (X-Y) and orientation (Z angle) of the crimp. Machine vision is therefore the system that helps the robot recognise the components to be inserted and identify deviations resulting from upstream process steps, such as crimping the cable, as well as from the unpredictable nature of the cables themselves.

"Without precise measurement, we would not be able to insert components with an accuracy of 0.1 mm, which is what we need to align the connector with the crimp," adds Dr. Nagele. The robot cell is equipped with a range of different hardware components to meet these challenges. In addition to a robot, these include robotic taping applicators, force-torque sensors, devices for accurately gripping the connectors, and a conveyor system. Cellios uses two 2D cameras for image processing.

On the software side, the system uses Cellios software and MVTec MERLIC. Munich-based MVTec Software develops technologically leading software for industrial machine vision worldwide. MERLIC makes it possible to automate complex applications quickly, even without specialized programming expertise.

Efficient application development

Cellios selected MERLIC because of its practical low-code approach: The clearly structured configuration interface makes it easy to select all required tools using drag and drop. Thanks to its intuitive user guidance, MERLIC enables users to get started quickly with developing a machine vision application without requiring in-depth knowledge of programming or image processing.

"For innovative companies such as Cellios, time to market is crucial. MERLIC provides the perfect leverage here: Its graphical user interface makes it possible to configure complex machine vision applications, such as the precise matching of very small components, quickly and efficiently without sacrificing the performance of proven algorithms," explains Ulf Schulmeyer, MERLIC Product Manager at MVTec.

MERLIC supports the application developed by Cellios in several ways. Within the image-processing workflow, powerful matching technologies enable the exact position and orientation of the crimps to be determined. In addition, MQTT and REST interfaces ensure seamless integration into the overall system, providing support that extends even beyond MERLIC's core role as machine vision software.

MERLIC's low setup effort and ease of use proved particularly advantageous: Two Cellios employees implemented the application using only videos and sample applications without any additional training. "Our collaboration with Cellios is an impressive demonstration of how machine vision is pushing the boundaries of what is possible in robotics. When robots learn to see with the same precision and flexibility as humans, even highly complex processes can be automated. MERLIC acts as the intelligence that translates image data into precise instructions for the robot," Schulmeyer adds.

Pioneering advancement in wire harness assembly

The developments by Cellios and its project partner TE Connectivity are pioneering. The prototype was presented in November 2025, and the official market launch is planned for early 2027. The benefits of the solution extend far beyond simply increasing productivity: Automation makes wire harness production economically attractive again in high-wage countries such as Germany.

Shorter transport routes also significantly reduce the carbon footprint of production, setting new standards for sustainability. In addition, digital monitoring of every insertion operation improves quality and enables complete traceability of the wire harnesses.

Based on initial feedback and customer discussions, Cellios is already planning to extend the automation solution to additional wire harness variants and new areas such as control cabinet wiring. Future machine vision systems are also expected to be used for self-healing processes and advanced quality inspections.