While AI-driven automation can increase the performance and safety of systems, humans should not be replaced in safety-critical systems but should be integrated to collaborate and mitigate each other’s limitations. The current trend in Industry 5.0 is towards human-centric collaborative paradigms, with an emphasis on collaborative intelligence (CI) or Hybrid Intelligent Systems. In this survey, we search and review recent work that employs AI methods for collaborative intelligence applications, specifically those that focus on safety and safety-critical industries. We aim to contribute to the research landscape and industry by compiling and analyzing a range of scenarios where AI can be used to achieve more efficient human–machine interactions, improved collaboration, coordination, and safety. We define a domain-focused taxonomy to categorize the diverse CI solutions, based on the type of collaborative interaction between intelligent systems and humans, the AI paradigm used and the domain of the AI problem, while highlighting safety issues. We investigate 91 articles on CI research published between 2014 and 2023, providing insights into the trends, gaps, and techniques used, to guide recommendations for future research opportunities in the fast developing collaborative intelligence field.

Collaborative intelligence (CI) involves human-machine interactions and is deemed safety-critical because their reliable interactions are crucial in preventing severe injuries and environmental damage. As these applications become increasingly data-driven, the reliability of CI applications depends on the quality of data, shaping the system’s ability to interpret and respond in diverse and often unpredictable environments. In this regard, it is important to adhere to data quality standards and guidelines, thus facilitating the advancement of these collaborative systems in industry. This study presents the challenges of data quality in CI applications within industrial environments, with two use cases that focus on the collection of data in Human-Robot Interaction (HRI). The first use case involves a framework for quantifying human and robot performance within the context of naturalistic robot learning, wherein humans teach robots using intuitive programming methods within the domain of HRI. The second use case presents real-time user state monitoring for adaptive multi-modal teleoperation, that allows for a dynamic adaptation of the system’s interface, interaction modality and automation level based on user needs. The article proposes a hybrid standardization derived from established data quality-related ISO standards and addresses the unique challenges associated with multi-modal HRI data acquisition. The use cases presented in this study were carried out as part of an EU-funded project, Collaborative Intelligence for Safety-Critical Systems (CISC).

'Correction to: Unlabeled Multimodal Datasets for Robust Emotion Recognition' published in 'Management of Digital EcoSystems'

Despite significant advances in teleoperated systems, optimal human performance remains a challenging task due to one key aspect, i.e. reduced situational awareness . Active telepresence is one of the major contributing factors affecting operator’s situational awareness. Providing the user with multiple perspectives of the remote environment can be very beneficial, although it may also introduce challenges in maintaining effective control. Prior work has largely examined discrete manipulation tasks using single-modality assessments, whereas this study applies a multimodal neuroergonomic approach to a continuous precision-cutting task, providing first insights into control–view alignment and multi-camera perception effects. In this work, we focus on two interaction and interface design factors: (a) control interaction factor , where we compare the effects of fixed and camera view-aligned control user interfaces on task-performance; (b) perception interface factor : the impact of different visual feedback configurations on operator attention and workload state, and interaction with the interface. A telerobotic system focused on a cutting task is chosen for this evaluation as it demands precision, depth perception, and also continuous feedback. A multimodal bio-sensor network is used to record operator-centric data, i.e Eye-tracking pupil measures, gaze measures and EEG signals, and assess the proposed interfaces using a neuroergonomics framework. User-study results show that using a view-aligned control frame in a multi-camera interface significantly improves cutting quality compared to using a fixed control frame, while the display of multiple camera perspectives in the same window is preferred to a single camera per window, promoting operator visual attention with no significant impact on the mental workload.