Personalized production is moving the progress of industrial automation forward, and demanding new tools for improving the decision-making of the operators. This paper presents a new, projection-based augmented reality system for assisting operators during electronic component assembly processes. The paper describes both the hardware and software solutions, and depicts the results obtained during a usability test with the new system.

This work presents an industrial bin-picking framework for robotics called PickingDK. The proposed framework employs a plugin based architecture, which allows it to integrate different types of sensors, robots, tools, and available open-source software and state-of-the-art methods. It standardizes the bin-picking process with a unified workflow based on generally defined plugin interfaces, which promises the hybridization of functional/virtual plugins for fast prototyping and proof-of-concept. It also offers different levels of controls according to the user’s expertise. The presented use cases demonstrate flexibility when building bin-picking applications under PickingDK framework and the convenience of exploiting hybrid style prototypes for evaluating specific steps in a bin-picking system, such as parameter fine-tuning and picking cell design.

In the context of smart manufacturing, the concept of Visual Computing is a key enabling technology for Industry 4.0. Visual Computing and Physically-based simulation enables the implementation of interactive, visual and (in most cases) non-disruptive solutions within the context of (a) the production process (off-line or in-line) the shop floor, (b) the interaction with customers and clients in the whole value chain, and/or (c) the product-service schemas. Technologies such as Industrial Big Data, Human-Robot Collaboration, IIOT & 5G, Cybersecurity, Cyber-Physical Systems, Semantic Technologies, Visual Computing and other related technologies have a strong impact in the new ways smart manufacturing is reconfiguring the production. This article presents a theoretical framework for the incorporation of Visual Computing and Physically-based Simulation technologies to Industry 4.0 and Operator 4.0 scenarios. This framework has been already implemented and supports different smart manufacturing scenarios, already running in many SME. Three practical study case scenarios (already deployed into SMEs) are presented and discussed.

In this study, we present a hybrid kinematic modeling approach for serial robotic manipulators, which offers improved accuracy compared to conventional methods. Our method integrates the geometric properties of the robot with ground truth data, resulting in enhanced modeling precision. The proposed forward kinematic model combines classical kinematic modeling techniques with neural networks trained on accurate ground truth data. This fusion enables us to minimize modeling errors effectively. In order to address the inverse kinematic problem, we utilize the forward hybrid model as feedback within a non-linear optimization process. Unlike previous works, our formulation incorporates the rotational component of the end effector, which is beneficial for applications involving orientation, such as inspection tasks. Furthermore, our inverse kinematic strategy can handle multiple possible solutions. Through our research, we demonstrate the effectiveness of the hybrid models as a high-accuracy kinematic modeling strategy, surpassing the performance of traditional physical models in terms of positioning accuracy.

The demand for flexible automation in manufacturing has increased, incorporating vision-guided systems for object grasping. However, a key challenge is in-hand error, where discrepancies between the actual and estimated positions of an object in the robot’s gripper impact not only the grasp but also subsequent assembly stages. Corrective strategies used to compensate for misalignment can increase cycle times or rely on pre-labeled datasets, offline training, and validation processes, delaying deployment and limiting adaptability in dynamic industrial environments. Our main contribution is an online self-supervised learning method that automates data collection, training, and evaluation in real time, eliminating the need for offline processes. Building on this, our system collects real-time data during each assembly cycle, using corrective strategies to adjust the data and autonomously labeling them via a self-supervised approach. It then builds and evaluates multiple regression models through an auto machine learning implementation. The system selects the best-performing model to correct the misalignment and dynamically chooses between corrective strategies and the learned model, optimizing the cycle times and improving the performance during the cycle, without halting the production process. Our experiments show a significant reduction in the cycle time while maintaining the performance.