Human Factors Issues in Implementation of AA to Complex Systems

This article presents a constrained review of human factors issues relevant to adaptive automation (AA), including designing complex system interfaces to support AA, facilitating human–computer interaction and crew interactions in adaptive system operations, and considering workload associated with AA management in the design of human roles in adaptive systems. Unfortunately, these issues have received limited attention in earlier reviews of AA. This work is aimed at supporting a general theory of human-centered automation advocating humans as active information processors in complex system control loops to support situation awareness and effective performance. The review demonstrates the need for research into user-centered design of dynamic displays in adaptive systems. It also points to the need for discretion in designing transparent interfaces to facilitate human awareness of modes of automated systems. Finally, the review identifies the need to consider critical human–human interactions in designing adaptive systems. This work describes important branches of a developing framework of AA research and contributes to the general theory of human-centered automation.

Context-sensitive function allocation can take two forms: (a) ‘adaptable automation’, where changes in the allocation of functions are initiated by the user, or (b) ‘adaptive automation’, where the automation triggers changes. However, operational experience suggests that neither approach by itself is sufficient and appropriate. This paper describes a hybrid dynamic function allocation scheme, in which the system and the operator collaborate on selecting and activating appropriate automation levels. The default mode of the system is adaptive automation, but operators can override system selections when they feel the need and have the time to do so. The effectiveness of the hybrid system was compared to fixed function allocations, to an adaptive scheme and to adaptable function allocation in the context of simulated robotic arm control tasks. The hybrid system improved performance and reduced workload in routine scenarios. The system was also preferred over the fixed and adaptive approach by the operators. However, these benefits can be explained mainly by the excessive use of high levels of automation in this condition. The findings have implications on future designs of dynamic function allocation schemes in complex systems.

During last years Adaptive Automation (AA) has received considerable attention in the academic community, in labs, in technology companies, because of the large use of automation in several domains (e.g. aviation; manufacturing; medicine; road, rail, and maritime transportation). AA is a potential solution to the problems associated with humanautomation interaction, regardless of the complexity of the application domain. The adaptive automation concept was firstly proposed about 30 years ago (Rouse, 1976), but technology has provided the empirical evidence of its effectiveness in more recent times. Several studies have shown that adaptive systems can regulate operator workload and enhance performance while preserving the benefits of automation (Hilburn et al., 1997; Kaber & Endsley, 2004; Moray et al., 2000; Prinzel et al., 2003). Still, inappropriate design of adaptive systems may even bring to a worse performance than full manual systems (Parasuraman et al., 1999). Therefore, methods and skills for designing adaptive automation systems should be fully mastered, before taking the implementation step. Before analyzing the concept and impact of adaptation features, the meaning and definition of automation should be defined, in order to stress how human characteristics and limitations influence the use (or misuse) of automation Andy Clark (2003) successfully tried to summarize the technological relationship between human and automated system: “humans have always been adept at dovetailing our minds and skills to the shape of our current tools and aids. But when those tools and aids start dovetailing back – when our technologies actively, automatically, and continually tailor themselves to us just as we do to them – then the line between tool and human becomes flimsy indeed”. Several researchers tried to define what adaptive automation is, using different and complementary concepts. In order to achieve a complete, if it is possible, definition of adaptive automation, it is needed to analyse the definition and the implication of automation itself. AA aims at optimizing the cooperation and at efficiently allocating labor between an automated system and its human users (Kay, 2006) and it can be considered as an

Investigation of multi-modal interface features for adaptive automation of a human–robot system

Two experiments are presented examining adaptive and adaptable methods for invoking automation. Empirical investigations of adaptive automation have focused on methods used to invoke automation or on automation-related performance implications. However, no research has addressed whether performance benefits associated with brain-based systems exceed those in which users have control over task allocations. Participants performed monitoring and resource management tasks as well as a tracking task that shifted between automatic and manual modes. In the first experiment, participants worked with an adaptive system that used their electroencephalographic signals to switch the tracking task between automatic and manual modes. Participants were also divided between high- and low-reliability conditions for the system-monitoring task as well as high- and low-complacency potential. For the second experiment, participants operated an adaptable system that gave them manual control over task allocations. Results indicated increased situation awareness (SA) of gauge instrument settings for individuals high in complacency potential using the adaptive system. In addition, participants who had control over automation performed more poorly on the resource management task and reported higher levels of workload. A comparison between systems also revealed enhanced SA of gauge instrument settings and decreased workload in the adaptive condition. The present results suggest that brain-based adaptive automation systems may enhance perceptual level SA while reducing mental workload relative to systems requiring user-initiated control. Potential applications include automated systems for which operator monitoring performance and high-workload conditions are of concern.

Situation awareness implications of adaptive automation for information processing in an air traffic control-related task

Complex adaptive systems (CAS) have been identified as being hard to comprehend, composed of multiple interacting components acting interdependently with overlapping functions aimed at adapting to external/environmental forces. The current theoretical model utilized the natural functions of teams, viewing teams as a complex adaptive system, to develop the structure of the theory of complex adaptive team systems (CATS). The CATS model was formulated around the components of complexity theory (interactions, nonlinearity, interdependency, heterogeneity, complex systems, emergence, self-organizing, and adaptability) to show its utility across multiple domains (the role of leadership, organizational learning, organizational change, collective cognitive structures, innovation, cross-business-unit collaborations). In theorizing the CATS model, a new level of analysis was implemented, the interactions between agents as a move toward emergence in complex systems. The CATS model ultimately provides a model for organizations/institutions to drive knowledge creation and innovation while operating in today's complexity.

This paper proposes a new backward‐type speech coding system (ADPCM‐AB) for wideband (7 kHz) speech and sound signals. In this system, a split‐band adaptive predictive coding scheme with gradient PARCOR lattice filter and a dynamic bit allocation scheme are employed, where quantization bits are dynamically allocated over the subbands (frequency), the subintervals (time), and the channels (stereo) in accordance with the distribution of the residual energies. They serve to remove the redundancies due to the periodic concentration of the prediction residual energy and the nonuniform nature of the speech spectrum. The ADPCM‐AB needs neither longer delay time than 4 ms nor transmission of side information parameters because the parameters for predictive coding and dynamic bit allocation are calculated with the locally decoded signals. It is clarified that the ADPCM‐AB system has the best speech quality among the conventional backward‐type coding systems. It is also shown that this system provides speech quality subjectively equivalent to 11‐bit linear PCM (176 kb/s) at 64 kb/s.

This article presents a theoretical framework for enhancing manufacturing productivity and safety by integrating cognitive ergonomics and artificial intelligence (AI). The framework addresses the critical gap in current research for a holistic approach to managing cognitive workload by proposing an integrated approach to managing cognitive workload and individual differences in modern manufacturing contexts. Despite the growing recognition of cognitive ergonomics, existing frameworks often fail to provide a unified model that incorporates AI and adaptive systems to optimize worker performance without negatively impacting mental workload or well-being. This paper proposes a comprehensive five-step theoretical framework integrating cognitive ergonomics principles, AI, and adaptive systems to optimize worker performance and productivity in manufacturing environments. The framework begins with assessing manufacturing operations and evaluates mental resource allocation to prevent overload. It optimizes cognitive and physical workload through real-time monitoring, integrates AI for dynamic task allocation, and establishes continuous feedback loops to adapt task demands, reduce errors, and enhance safety. This paper aims to contribute to developing predictive models for cognitive workload and tailored technologies for cognitive load reduction, filling a significant gap in existing research. The proposed framework provides a standardized approach to improving manufacturing operations by combining cognitive ergonomics with adaptive automation systems. Ultimately, it aims to promote worker well-being and performance, ensuring that AI and adaptive systems complement, rather than detract from, cognitive capacity while reducing cognitive workload, mental pressure, and performance declines in high-workload environments.

With the creation of unmanned systems the development of ergonomics has entered a new stage in studying human-machine interaction and exacerbated safety issues. The requirements for safety, resistance to failures and reliability of the systems and their main connection – the human operator, were changed. New challenges – new human problems in digital systems. Digitization has made it possible to create unmanned systems, but it has also created an ergonomic contradiction between intentions and results. Its essence is that, in contrast to the expected increase in efficiency and safety, the increase in unmanned systems automation leads to an increase in the risks associated with human influence. Unmanned aerial systems have unique ergonomic challenges related to the specifics of the UAV operator and the technical features of the UAVs themselves as complex systems. In this regard, it is relevant to analyze the reasons for the continuing manifestations of the human factor phenomenon in the functioning of unmanned systems and the search for ways to reduce them. The purpose is to study the human factor problem in complex systems that use information and communication technologies, using the example of unmanned aircraft systems. The article takes a critical look at the human factor issues in unmanned aviation that are not being addressed by existing approaches. An iceberg model of change management in the safety of complex systems is proposed. It is shown that the human factor in unmanned systems arises and severely decreases because of the nontransdisciplinary nature of the education of modern engineers and operators. And the essential role in overcoming this problem is knowledge aimed at understanding the capabilities and limitations of a person as the main link of the system, which then makes decisions in the management process. It is shown that it is necessary to pay considerable attention to the development of ergonomic thinking among everyone whose activities relate to the life cycle of a complex system. That is, it is the transdisciplinarity of the education of specialists that allows for reducing the specified risks of human-machine interaction.

In video-on-demand (VOD) systems, as the size of the buffer allocated to user requests increases, initial latency and memory requirements increase. Hence, the buffer size must be minimized. The existing static buffer allocation scheme, however, determines the buffer size based on the assumption that the system is in the fully loaded state. Thus, when the system is in a partially loaded state, the scheme allocates a buffer larger than necessary to a user request. This paper proposes a dynamic buffer allocation scheme that allocates to user requests buffers of the minimum size in a partially loaded state as well as in the fully loaded state. The inherent difficulty in determining the buffer size in the dynamic buffer allocation scheme is that the size of the buffer currently being allocated is dependent on the number of and the sizes of the buffers to be allocated in the next service period. We solve this problem by the predict-and-enforce strategy, where we predict the number and the sizes of future buffers based on inertia assumptions and enforce these assumptions at runtime. Any violation of these assumptions is resolved by deferring service to the violating new user request until the assumptions are satisfied. Since the size of the current buffer is dependent on the sizes of the future buffers, the size is represented by a recurrence equation. We provide a solution to this equation, which can be computed at the system initialization time for runtime efficiency. We have performed extensive analysis and simulation. The results show that the dynamic buffer allocation scheme reduces initial latency (averaged over the number of user requests in service from one to the maximum capacity) to 1 ÷ 29.4 n 1 ÷ 11.0 of that for the static one and, by reducing the memory requirement, increases the number of concurrent user requests to 2.36 ∼ 3.25 times that of the static one when averaged over the amount of system memory available. These results demonstrate that the dynamic buffer allocation scheme significantly improves the performance and capacity of VOD systems.

The complexity of problems facing society continues to grow, and decision-makers and problem-solvers are finding many of today's emerging problems to be beyond their capability to adequately address. There is agreement in the literature that problems of this nature are complex system problems, inextricably linked to some highly complex system of systems. Establishing a clear understanding of the specific complex system context is fundamental to the process of understanding and analyzing complex systems and complex system problems across all of the different systems-based disciplines. While complex system context is widely referred to in systems literature, there is no clear characterization of exactly what system context is, making this foundational system concept ambiguous. This research addressed this gap in the systems body of knowledge by providing the needed detail and clarity to the concept of complex system context. A rigorous research methodology, employing the grounded theory method, was used to analyze data collected through a series of semi-structured interviews conducted with individuals reflecting a wide range of systems education and practical experience. Two research questions were identified as integral to increasing the understanding of context within complex systems. (1) What are the constituent elements of complex system context, and what attributes and dimensions characterize these elements? (2) What systems-based framework can be developed for constructing and articulating complex system context? Using the grounded theory method, a theory of system context was constructed, adding to the systems body of knowledge and substantiating a comprehensive and unambiguous theoretical construct for system context within complex systems. Then, based on this theory, a conceptual model to articulate and capture system-specific complex system context was developed---the Complex System Contextual Framework (CSCF). The CSCF shows significant promise for contribution to systems practitioners by supporting the future development of tools to help practitioners capture system context as a part of complex system problem formulation. The research also made a contribution in the area of research methodologies by furthering the use of the grounded theory method in the engineering management and systems engineering domain, an area where its application has been very limited.

This article investigates resource allocation in ATM networks and emphasizes bandwidth allocation. Resource allocation methods are categorized, and static and dynamic allocation strategies are compared. Dynamic allocation uses actual traffic behavior, while static allocation uses only the reference traffic condition given a priori. Examples of dynamic allocation strategies are available bit rate flow control, dynamic connection admission control, and dynamic VP bandwidth control. Dynamic resource allocation is shown to be promising for situations where the a priori reference model is unclear.

Linguistic Geometry for autonomous navigation

On Navy ships, technological developments enable crews to work more efficiently and effectively. However, in such complex, autonomous, and information-rich environments a competition for the users' attention is going on between different information items, possibly leading to a cognitive overload. This overload originates in the limitations of human attention and constitutes a well-known and well-studied bottleneck in human information processing. The concept of adaptive automation promises a solution to the overwhelmed operator by shifting the amount of work between the human and the system in time, while maintaining a high level of situation awareness. One of the most critical challenges in developing adaptive human-machine collaboration concerns the design of a trigger mechanism. This paper discusses and evaluates a number of possible triggers for the usage in closed-loop adaptive automation from the perspective of command and control.