Sichao Liu

The application of artificial intelligence (AI) in industry is accelerating the shift from traditional automation to intelligent systems with perception and cognition. Vision language-action (VLA) models have been a key paradigm in AI to unify perception, reasoning, and control. Has the performance of the VLA models met the industrial requirements? In this paper, from the perspective of industrial deployment, we compare the performance of existing state-of-the-art VLA models in industrial scenarios and analyze the limitations of VLA models for real-world industrial deployment from the perspectives of data collection and model architecture. The results show that the VLA models retain their ability to perform simple grasping tasks even in industrial settings after fine-tuning. However, there is much room for performance improvement in complex industrial environments, diverse object categories, and high precision placing tasks. Our findings provide practical insight into the adaptability of VLA models for industrial use and highlight the need for task-specific enhancements to improve their robustness, generalization, and precision.

In Industry 4.0 applications, dynamic environmental interference induces highly nonlinear and strongly coupled interactions between the environmental state and robotic behavior. Effectively representing dynamic environmental states through multimodal sensor data fusion remains a critical challenge in current robotic datasets. To address this, an industrial-grade multimodal interference dataset is presented, designed for robotic perception and control under complex conditions. The dataset integrates multi-dimensional interference features including size, color, and lighting variations, and employs high-precision sensors to synchronously collect visual, torque, and joint-state measurements. Scenarios with geometric similarity exceeding 85\% and standardized lighting gradients are included to ensure real-world representativeness. Microsecond-level time-synchronization and vibration-resistant data acquisition protocols, implemented via the Robot Operating System (ROS), guarantee temporal and operational fidelity. Experimental results demonstrate that the dataset enhances model validation robustness and improves robotic operational stability in dynamic, interference-rich environments. The dataset is publicly available at:https://modelscope.cn/datasets/Liaoh_LAB/Liaohe-CobotMagic-PnP.

Digital servitization (DS) enabled by the Industrial Internet of Things (IIoT) is essential for securing long-term competitiveness in manufacturing. The literature identifies the need for developing data models for multichannel communications across IIoT devices that fulfil the DS vision. This is crucial for avoiding isolated systems based on proprietary solutions and for promoting data sharing and interoperability across existing and future DS applications. Accordingly, this study proposes a data model for multichannel communication that facilitates IIoT-enabled DS for smart production logistics (SPL). We present three findings from a case study focussing on material handling in a manufacturing company. First, this study provides a model with four modelling profiles, including IIoT devices, databases, and services for multichannel communication. Second, it shows how the proposed modelling profiles transfer information across monitoring, control, optimisation, and autonomous decision services. Third, it presents the operational benefits of applying the proposed data models, including improvements in the delivery, makespan, and energy of material handling. These findings are essential for capturing, processing, and transferring information across products, services, and software databases in IIoT-enabled DS for SPL. They are relevant for manufacturing managers and academics and improve our understanding of IIoT-enabled DS's deployment for SPL in manufacturing.

In human–robot collaborative assembly, leveraging multimodal commands for intuitive robot control remains a challenge from command translation to efficient collaborative operations. This article investigates multimodal data-driven robot control for human–robot collaborative assembly. Leveraging function blocks, a programming-free human–robot interface is designed to fuse multimodal human commands that accurately trigger defined robot control modalities. Deep learning is explored to develop a command classification system for low-latency and high-accuracy robot control, in which a spatial-temporal graph convolutional network is developed for a reliable and accurate translation of brainwave command phrases into robot commands. Then, multimodal data-driven high-level robot control during assembly is facilitated by the use of event-driven function blocks. The high-level commands serve as triggering events to algorithms execution of fine robot manipulation and assembly feature-based collaborative assembly. Finally, a partial car engine assembly deployed to a robot team is chosen as a case study to demonstrate the effectiveness of the developed system.

In human–robot collaborative assembly, robots are often required to dynamically change their preplanned tasks to collaborate with human operators in close proximity. One essential requirement of such an environment is enhanced flexibility and adaptability, as well as reduced effort on the conventional (re)programming of robots, especially for complex assembly tasks. However, the robots used today are controlled by rigid native codes that cannot support efficient human–robot collaboration. To solve such challenges, this article presents a novel function block-enabled multimodal control approach for symbiotic human–robot collaborative assembly. Within the context, event-driven function blocks as reusable functional modules embedded with smart algorithms are used for the encapsulation of assembly feature-based tasks/processes and control commands that are transferred to the controller of robots for execution. Then, multimodal control commands in the form of sensorless haptics, gestures, and voices serve as the inputs of the function blocks to trigger task execution and human-centered robot control within a safe human–robot collaborative environment. Finally, the performed processes of the method are experimentally validated by a case study in an assembly work cell on assisting the operator during the collaborative assembly. This unique combination facilitates programming-free robot control and the implementation of the multimodal symbiotic human–robot collaborative assembly with the enhanced adaptability and flexibility.