LAUSR

Modern factories are evolving towards higher autonomy and increased resilience by advancing the adoption of digital tools for designing, deploying and operating production systems. Regarding assembly processes in particular, manufacturing systems need to cope with increased product variety and higher product complexity which all challenge the capacity of the factory to respond efficiently (Chryssolouris 2006; Hu et al. 2011). This special issue has compiled a number of novel approaches towards advancing the operation of assembly systems. The main research areas investigated are human aspects in assembly, human–robot interaction and collaboration, assembly systems planning and control industrial robot technology and robotic perception and machine learning (Makris 2021). Human-centred performance management in manual assembly has been studied with the help of gamification methods and KPIs. This approach investigates the effect of human-centered performance management concerning operational performance and work motivation of shop floor employees. While to date, the concept of gamification has been applied in numerous fields, yet hardly any related work provides empirical findings for the production environment. Quantitative and qualitative observations show that the provision of gamified metrics-based information proves to be a motivation driver. Another key aspect of manual assembly is the personnel task allocation taking into consideration skills and remote guidance based on Augmented Reality and Intelligent Decision-Making. In the realm of the fourth industrial revolution, the flawless and continuous operation of the technology-rich workplaces is a challenging problem. The assessment of technician skills could facilitate initially the adaptation of guidance instructions as well as the job allocation to their unique attributes and qualities. Hence, tools for assessing human resources skills, job allocation and task-related support based on intelligent decisionmaking and Augmented Reality are investigated (Krüger et al. 2017; Wang et al. 2019). Furthermore, people need to interact with machines and multi-modal approaches for monitoring and control in Smart Factories are studied. Although the increasing level of automation in industry, manual or semiautomated e.g. cobot equipped assembly stations are common and inevitable for complex assembly tasks. The transformation to smart processes in manufacturing leads to a higher deployment of data-driven approaches to support the worker. Upcoming technologies in this context are oftentimes based on the modalities such as voice, gesture and intention-recognition, -monitoring or -control (Michalos et al. 2018; Papanastasiou et al. 2019). Over the past decades, robots have been extensively deployed in multiple industries to perform preprogrammed tasks. However, some tasks are still too complex or expensive to be performed by a robotic system alone. More recently, industrial robots have been taken out of their cages, being more present in dynamic and uncertain environments, interacting in the close vicinity of human operators. When people need to interact with robots to handle complex processes, sensors are typically employed to help robots perceive the interaction intention of people. For example, the idea of human–robot co-manipulation of flexible materials has been based on fusing torque sensor and skeleton tracking data from a camera in order to control a mobile manipulator in an intuitive manner, by exploiting the intelligence of the operator as much as possible (Villani et al. 2018; Bänziger, Kunz, and Wegener 2018; Pellegrinelli et al. 2017). Cooperating with robots also requires to be able to identify and classify assembly operations. Imagebased classification of MTM operations in assembly using recurrent neural networks enables the acquisition and transfer of data from manual assembly workstations into a digital environment. Based on the MTM method, assembly processes are transformed into short, discrete and basic operations that are recognised by means of 3D image processing and processed by a multilayer neural network. Moreover, assembly systems planning has to consider aspects of changing requirements, and as such, INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2023, VOL. 36, NO. 1, 1–2 https://doi.org/10.1080/0951192X.2022.2163555