Figure 5 - uploaded by Omer Tsimhoni
Content may be subject to copyright.
Source publication
Queueing Network-Model Human Processor (QN-MHP) is a computational architecture that integrates two complementary approaches to cognitive modeling: the queueing network approach and the symbolic approach (exemplified by the MHP/GOMS family of models, ACT-R, EPIC, and SOAR). Queueing networks are particularly suited for modeling parallel activities...
Similar publications
In human-machine-interaction, interruptability and resumption of different tasks are common aspects to influence human performance. To understand human behavior in such situations, we conducted a multitasking experiment where subjects had to perform a test of attention when driving. In this paper, we present an ACT-R/PM model on how people perform...
Performance modeling has been made easier by architectures which package psychological theory for reuse at different levels. Both CPM-GOMS, which packages theory at the task level, and ACT-R, which packages theory at the lower level of rules for perceptual-motor interaction, have been shown to be useful. This paper describes ACT-Stitch, a framework...
Citations
... In determining the most pertinent factors to depict the driver state for this dataset, we took into account established driver models and cognitive architectures. Adaptive Control of Thought-Rational (ACT-R) 21 , Queueing Network-Model Human Processor (QN-MHP) 22 , and CLARION 23 are a few models recurrently employed for both qualitative and computational research 24 . ACT-R is a cognitive architecture that designates multiple modules to the driver, encompassing the goal, memory, perceptual, and motor functions. ...
In driver monitoring various data types are collected from drivers and used for interpreting, modeling, and predicting driver behavior, and designing interactions. Aim of this contribution is to introduce manD 1.0, a multimodal dataset that can be used as a benchmark for driver monitoring in the context of automated driving. manD is the short form of human dimension in automated driving. manD 1.0 refers to a dataset that contains data from multiple driver monitoring sensors collected from 50 participants, gender-balanced, aged between 21 to 65 years. They drove through five different driving scenarios in a static driving simulator under controlled laboratory conditions. The automation level (SAE International, Standard J3016) ranged from SAE L0 (no automation, manual) to SAE L3 (conditional automation, temporal). To capture data reflecting various mental and physical states of the subjects, the scenarios encompassed a range of distinct driving events and conditions. manD 1.0 includes environmental data such as traffic and weather conditions, vehicle data like the SAE level and driving parameters, and driver state that covers physiology, body movements, activities, gaze, and facial information, all synchronized. This dataset supports applications like data-driven modeling, prediction of driver reactions, crafting of interaction strategies, and research into motion sickness.
... Most underlying theories are conceptual or empirical, so the context of use is limited. Typical models like ACT-R [35], QN-MHP [36], and SOAR [37], etc. It is worth noting that the distinction between the three types is not absolute. ...
The human digital twin (HDT) emerges as a promising human-centric technology in Industry 5.0, but challenges remain in human modeling and simulation. Digital human modeling (DHM) provides solutions for modeling and simulating human physical and cognitive aspects to support ergonomic analysis. However, it has limitations in real-time data usage, personalized services, and timely interaction. The emerging HDT concept offers new possibilities by integrating multi-source data and artificial intelligence for continuous monitoring and assessment. Hence, this paper reviews the evolution from DHM to HDT and proposes a unified HDT framework from a human factors perspective. The framework comprises the physical twin, the virtual twin, and the linkage between these two. The virtual twin integrates human modeling and AI engines to enable model-data-hybrid-enabled simulation. HDT can potentially upgrade traditional ergonomic methods to intelligent services through real-time analysis, timely feedback, and bidirectional interactions. Finally, the future perspectives of HDT for industrial applications as well as technical and social challenges are discussed. In general, this study outlines a human factors perspective on HDT for the first time, which is useful for cross-disciplinary research and human factors innovation to enhance the development of HDT in industry.
... The model predicted the amount of time that unskilled users spent finding a key on a keypad and pressing it repeatedly. The QN approach (Liu et al., 2006a) has been improved with some error modeling capabilities such as a wrongly processed entity or character (Wu and Liu, 2008) and errors in numerical typing (Lin and Wu, 2012). However, these errors were meant to account for experts potentially committing errors due to their cognitive workload rather than to model novices' perceptual, cognitive, and motor characteristics. ...
Cognitive performance models have been used in several human factors domains such as driving and human-computer interaction. However, most models are limited to expert performance with rough adjustments to consider novices despite prior studies suggesting novices' cognitive, perceptual, and motor behaviors are different from experts. The objective of this study was to develop a cognitive performance model for novice law enforcement officers (N-CPM) to model their performance and memory load while interacting with in-vehicle technology. The model was validated based on a ride-along study with 10 novice law enforcement officers (nLEOs). The findings suggested that there were no significant differences between the N-CPM and observation data in most cases, while the results of the benchmark model were different from that of N-CPM. The model can be applied to improve future nLEO's patrol mission performance through redesigning in-vehicle technologies and training methods to reduce their workload and driving distraction.
... The modeling of driver errors is a distinct difference compared to those predictive models. Original cognitive models such as ACT-R [97], Soar [98], and QN-MHP [99] are based on psychological cognitive architectures. These models can facilitate the understanding of driver behavior in the context of general human abilities and constraints. ...
Driver models play a vital role in developing and verifying autonomous vehicles (AVs). Previously, they were mainly applied in traffic flow simulation to model driver behavior. With the development of AVs, driver models attract much attention again due to their potential contributions to AV safety assessment. The simulation-based testing method is an effective measure to accelerate AV testing due to its safe and efficient characteristics. Nonetheless, realistic driver models are prerequisites for valid simulation results. Additionally, an AV is assumed to be at least as safe as a careful and competent driver, which is modeled by driver models as well. Therefore, driver models are essential for AV safety assessment from the current perspective. However, no comparison or discussion of driver models is available regarding their utility to AVs in the last five years despite their necessities in the release of AVs. This motivates us to present a comprehensive survey of driver models in the paper and compare their applicability. Requirements for driver models as applied to AV safety assessment are discussed. A summary of driver models for simulation-based testing and AV benchmarks is provided. Evaluation metrics are defined to compare their strengths and weaknesses. Finally, potential gaps in existing driver models are identified, which provide direction for future work. This study gives related researchers especially regulators an overview and helps them to define appropriate driver models for AV safety assessment.
... Several research efforts, notably ACT-R [17] and QN-MHP [18], have used cognitive architectures to develop models that simulate human driving behavior. Salvucci et al. utilized ACT-R to model lane following and changing behaviors. ...
A typical approach for scenario-based testing of autonomous vehicles involves participating vehicles that are modeled using static, predetermined, and time-stamped tra-jectory information. These scenarios not only fail to capture the behavioral variability of human drivers but also limit the usability of the scenario with continuous software updates of the autonomous vehicles, as surrounding vehicles remain static while the AVs' behavior changes due to system updates. We present a human driver behavior model called CogMod, which is based on a hybrid cognitive architecture to represent human cognition during driving. This model surpasses the current state of the art in modeling human driving behavior in several ways. Contrary to most implementable models, where control is directly based on observed variables, CogMod actions rely on a rich internal representation. This internal representation is the result of a novel perception mechanism that enables the CogMod driver to have a selective update of the surrounding environment. The model is capable of simulating human drivers' perceptive and cognitive limitations, thus capturing human driving variability. To evaluate our model, we compare CogMod-generated microscopic distributions with real-world driving data obtained from the HighD dataset. Our result shows that our model can augment existing real-world driving scenarios, thereby increasing their complexity and criticality for testing autonomous vehicles.
... IMPRINT be naturally used for modeling all sequences of tasks at hand, while ACT-R is a natural environment for predicting human performance for each task. Another example is the composite cognitive architecture QN-MHRP from [220] which connects a queuing network model with a cognitive architecture in order to study human performance on concurrent activities. Queuing networks are well-suited for modeling parallel activities, while cognitive architectures are well-suited for predicting a person's action on a specific task. ...
We survey the landscape of human operator modeling ranging from the early cognitive models developed in artificial intelligence to more recent formal task models developed for model-checking of human machine interactions. We review human performance modeling and human factors studies in the context of aviation, and models of how the pilot interacts with automation in the cockpit. The purpose of the survey is to assess the applicability of available state-of-the-art models of the human operators for the design, verification and validation of future safety-critical aviation systems that exhibit higher-level of autonomy, but still require human operators in the loop. These systems include the single-pilot aircraft and NextGen air traffic management. We discuss the gaps in existing models and propose future research to address them.
... After the initial models, various CPMs emerged applying cognitive science theory [34]. These models included Goals, Operators, Methods, and Selection (GOMS) rules [7], Adaptive Control of Thought-Rational (ACT-R) [2], Executive-Process Interactive Control (EPIC) [21], State, Operator, and Result (SOAR) [25], and Queuing Network-Model Human Processor (QN-MHP) [30]. ...
... Lastly, QN-MHP is a computational cognitive architecture that integrates the mathematical framework of queuing network theory with MHP [30]. Based on a network structure of 20 process units (e.g. ...
... He demonstrated through simulation that the model is capable of mimicking basic patterns found in RT and accuracy data. There are other precedent theories and models that conceptualize cognitive processing as being both serial and parallel, for instance, the models proposed by Harris, Shaw, and Bates (1979); Fisher (1982Fisher ( , 1984; Miller (1993) ;Liu (1996Liu ( , 2013; Liu, Feyen, and Tsimhoni (2006); and Wu and Liu (2008). Some of them have been stated as quantitative models, but the time-dependent limited-channel model by Fisher (1982) is the only one developed specifically for visual search. ...
Understanding how attentional resources are deployed in visual processing is a fundamental and highly debated topic. As an alternative to theoretical models of visual search that propose sequences of separate serial or parallel stages of processing, we suggest a queueing processing structure that entails a serial transition between parallel processing stages. We develop a continuous-time queueing model for standard visual search tasks to formalize and implement this notion. Specified as a finite-time, single-line, multiserver queueing system, the model accounts for both accuracy and response time (RT) data in visual search on a distributional level. It assumes two stages of processing. Visual stimuli first go through a massively parallel preattentive stage of feature encoding. They wait if necessary and then enter a limited-capacity attentive stage serially where multiple processing channels (''servers'') integrate features of several stimuli in parallel. A core feature of our model is the serial transition from the unlimited-capacity preattentive processing stage to the limited-capacity attentive processing stage. It enables asynchronous attentive processing of multiple stimuli in parallel and is more efficient than a simple chain of two successive, strictly parallel processing stages. The model accounts for response errors by means of two underlying mechanisms, namely, imperfect processing of the servers and, in addition, incomplete search adopted by the observer to maximize search efficiency under an accuracy constraint. For statistical inference, we develop a Monte-Carlo-based parameter estimation procedure, using maximum likelihood (ML) estimation for accuracy-related parameters and minimum distance (MD) estimation for RT-related parameters. We fit the model to two large empirical data sets from two types of visual search tasks. The model captures the accuracy rates almost perfectly and the observed RT distributions quite well, indicating a high explanatory power. The number of independent parallel processing channels that explain both data sets best was five. We also perform a Monte-Carlo model uncertainty analysis and show that the model with the correct number of parallel channels is selected for more than 90% of the simulated samples.
... The goal of cognitive models is to simulate the human cognition process while driving, which includes perception, recognition, judgment, and operation. Original cognitive models such as ACT-R [97], Soar [98] and QN-MHP [99] are based on psychological cognitive architectures. These models can facilitate the understanding of driver behavior in the context of general human abilities and constraints. ...
Driver models play a vital role in developing and verifying autonomous vehicles (AVs). Previously, they are mainly applied in traffic flow simulation to model realistic driver behavior. With the development of AVs, driver models attract much attention again due to their potential contributions to AV certification. The simulation-based testing method is considered an effective measure to accelerate AV testing due to its safe and efficient characteristics. Nonetheless, realistic driver models are prerequisites for valid simulation results. Additionally, an AV is assumed to be at least as safe as a careful and competent driver. Therefore, driver models are inevitable for AV safety assessment. However, no comparison or discussion of driver models is available regarding their utility to AVs in the last five years despite their necessities in the release of AVs. This motivates us to present a comprehensive survey of driver models in the paper and compare their applicability. Requirements for driver models in terms of their application to AV safety assessment are discussed. A summary of driver models for simulation-based testing and AV certification is provided. Evaluation metrics are defined to compare their strength and weakness. Finally, an architecture for a careful and competent driver model is proposed. Challenges and future work are elaborated. This study gives related researchers especially regulators an overview and helps them to define appropriate driver models for AVs.
... In this scenario a human subject undertakes a simultaneous CCTV monitoring task while multiple sensors track the environment. Therefore, our system can be widely utilized in various multi-human-multiagents system task scenarios, such as security monitoring [49], [64], air traffic management [50], [65], [66], and performance checking [51], [67]. Additionally, we only validated the AWAC on homogeneous missions and robot platforms, which limits its generalizability. ...
The interaction and collaboration between humans and multiple robots represent a novel field of research known as human multi-robot systems. Adequately designed systems within this field allow teams composed of both humans and robots to work together effectively on tasks such as monitoring, exploration, and search and rescue operations. This paper presents a deep reinforcement learning-based affective workload allocation controller specifically for multi-human multi-robot teams. The proposed controller can dynamically reallocate workloads based on the performance of the operators during collaborative missions with multi-robot systems. The operators' performances are evaluated through the scores of a self-reported questionnaire (i.e., subjective measurement) and the results of a deep learning-based cognitive workload prediction algorithm that uses physiological and behavioral data (i.e., objective measurement). To evaluate the effectiveness of the proposed controller, we use a multi-human multi-robot CCTV monitoring task as an example and carry out comprehensive real-world experiments with 32 human subjects for both quantitative measurement and qualitative analysis. Our results demonstrate the performance and effectiveness of the proposed controller and highlight the importance of incorporating both subjective and objective measurements of the operators' cognitive workload as well as seeking consent for workload transitions, to enhance the performance of multi-human multi-robot teams.
