Human Team Research Articles

The Inner Loop of Collective Human-Machine Intelligence.

With the rise of artificial intelligence (AI) and the desire to ensure that such machines work well with humans, it is essential for AI systems to actively model their human teammates, a capability referred to as Machine Theory of Mind (MToM). In this paper, we introduce the inner loop of human-machine teaming expressed as communication with MToM capability. We present three different approaches to MToM: (1) constructing models of human inference with well-validated psychological theories and empirical measurements; (2) modeling human as a copy of the AI; and (3) incorporating well-documented domain knowledge about human behavior into the above two approaches. We offer a formal language for machine communication and MToM, where each term has a clear mechanistic interpretation. We exemplify the overarching formalism and the specific approaches in two concrete example scenarios. Related work that demonstrates these approaches is highlighted along the way. The formalism, examples, and empirical support provide a holistic picture of the inner loop of human-machine teaming as a foundational building block of collective human-machine intelligence.

Survey of ticks and tick-borne pathogens in wild chimpanzee habitat in Western Uganda

BackgroundTicks and tick-borne pathogens significantly impact both human and animal health and therefore are of major concern to the scientific community. Knowledge of tick-borne pathogens is crucial for prescription of mitigation measures. In Africa, much research on ticks has focused on domestic animals. Little is known about ticks and their pathogens in wild habitats and wild animals like the endangered chimpanzee, our closest relative.MethodsIn this study, we collected ticks in the forested habitat of a community of 100 chimpanzees living in Kibale National Park, Western Uganda, and assessed how their presence and abundance are influenced by environmental factors. We used non-invasive methods of flagging the vegetation and visual search of ticks both on human team members and in chimpanzee nests. We identified adult and nymph ticks through morphological features. Molecular techniques were used to detect and identify tick-borne piroplasmids and bacterial pathogens.ResultsA total of 470 ticks were collected, which led to the identification of seven tick species: Haemaphysalis parmata (68.77%), Amblyomma tholloni (20.70%), Ixodes rasus sensu lato (7.37%), Rhipicephalus dux (1.40%), Haemaphysalis punctaleachi (0.70%), Ixodes muniensis (0.70%) and Amblyomma paulopunctatum (0.35%). The presence of ticks, irrespective of species, was influenced by temperature and type of vegetation but not by relative humidity. Molecular detection revealed the presence of at least six genera of tick-borne pathogens (Babesia, Theileria, Borrelia, Cryptoplasma, Ehrlichia and Rickettsia). The Afrotopical tick Amblyomma tholloni found in one chimpanzee nest was infected by Rickettsia sp.ConclusionsIn conclusion, this study presented ticks and tick-borne pathogens in a Ugandan wildlife habitat whose potential effects on animal health remain to be elucidated.Graphical

Adaptable Mixed-Reality Sensorimotor Interface for Human-Swarm Teaming: Person with Limb Loss Case Study and Field Experiments

This paper presents the design, evaluation, and field experiment of the innovative Adapt- able Human-Swarm Teaming ( α -SWAT) interface developed to support military field operations. Human-swarm teaming requires collaboration between a team of humans and a team of robotic agents for strategic decision-making and task performance. α -SWAT allows multiple human team members with different roles, physical capabilities, or preferences to interact with the swarm via a configurable, multimodal user interface (UI). The system has an embedded task allocation algorithm for the rapid assignment of tasks created by the mission planner to the swarm. The multimodal UI supports swarm visualization via a mixed reality display or a conventional 2D display, human gesture inputs via a camera or an electromyography device, tactile feedback via a vibration motor or implanted peripheral nerve interface, and audio feedback. In particular, the UI system interfacing with the implanted electrodes through a neural interface enables gesture detection and tactile feedback for individuals with upper limb amputation to participate in human-swarm teaming. The multimodality of α -SWAT’s UI adapts to the needs of three different roles of the human team members: Swarm Planner, Swarm Tactician Rear, and Swarm Tactician Forward. A case study evaluated the functionality and usability of α -SWAT to enable a participant with limb loss and an implanted neural interface to assign three tasks to a simulated swarm of 150 robotic agents. α -SWAT was also used to visualize live telemetry from 40 veridical robotic agents for multiple simultaneous human participants at a field experiment.

Impact of Transparency and Explanations on Trust and Situation Awareness in Human–Robot Teams

Urban Search and Rescue (USAR) missions continue to benefit from the incorporation of human–robot teams (HRTs). USAR environments can be ambiguous, hazardous, and unstable. The integration of robot teammates into USAR missions has enabled human teammates to access areas of uncertainty, including hazardous locations. For HRTs to be effective, it is pertinent to understand the factors that influence team effectiveness, such as having shared goals, mutual understanding, and efficient communication. The purpose of our research is to determine how to (1) better establish human trust, (2) identify useful levels of robot transparency and robot explanations, (3) ensure situation awareness, and (4) encourage a bipartisan role amongst teammates. By implementing robot transparency and robot explanations, we found that the driving factors for effective HRTs rely on robot explanations that are context-driven and are readily available to the human teammate.

The effect of cognitive workload on decision authority assignment in human–robot collaboration

Human–robot collaboration in dynamic industrial environments warrants robot flexibility and shifting between tasks. Adaptive robot behavior unavoidably carries decision-making needs regarding task allocation and scheduling. Such decisions can be made either by the human team members or autonomously, by the robot’s controlling algorithm. Human authority may help preserve situational awareness but increases mental demands due to increased responsibilities. Conversely, granting authority to the robot can offload the operator, at the cost of reduced intervention readiness. This paper aims to investigate the question of decision authority assignment in a human–robot team, in terms of performance, perceived workload and subjective preference. We hypothesized that the answer is influenced by the cognitive workload imposed on the human operator by the work process. An experiment with 21 participants was conducted, in which decision authority and induced workload through a secondary task were varied between trials. Results confirmed that operators can support the robot better when decision authority is allocated according to their workload. However, operator decision authority (a) may cause inferior performance at any secondary tasks performed in parallel with robot supervision and (b) increases perceived workload. Subjective preference was found to be evenly divided between the two levels of decision authority, and unaffected by task difficulty. In brief, if human–robot team performance is a priority, humans should be granted decision authority when their overall workload allows it. In high-workload conditions, system decision-making algorithms should be developed. Nonetheless, process designers should be mindful of the interpersonal differences between operators who are destined to collaborate with robots.

Construal level theory in the design of informational systems

In the context of human-machine teaming, we are observing new kinds of automated and “intelligent” applications that effectively model and manage both producer and consumer aspects of information presentation. Information produced by the application can be easily accessed by the user at multiple levels of abstraction, depending on the user’s current context and necessity. The research described in this article applies this concept of information abstraction to complex command and control systems in which distributed autonomous systems are managed by multiple human teams. We explore three multidisciplinary and foundational concepts that can be used to design information flow in human-machine teaming situations: 1) formalizing a language we call “RECITAL” (Rules of Engagement, Commander’s Intent, and Transfer of Authority Language), which defines the information flow based on concepts of intent, rules, and delegated authority; 2) applying this language to well-established models of human-machine distributed teams represented as a systemic control hierarchy; and 3) applying construal level theory from social psychology as a means to guide the producer-consumer model of the information abstractions. All three of these are integrated into a novel user interface concept designed to make information available to both human and machine actors based on task-oriented decision criteria. In this research, we describe a conceptual model for future information design to inform shared control and decision-making across distributed human and machine teams. We describe the theoretical components of the concepts and present the conceptual approach to designing such systems. Using the concept, we describe a prototype user interface to situationally manage the information in a mission application.

Trust in an AI versus a Human teammate: The effects of teammate identity and performance on Human-AI cooperation

Recent advances in artificial intelligence (AI) enable researchers to create more powerful AI agents that are becoming competent teammates for humans. However, human distrust of AI is a critical factor that may impede human-AI cooperation. Although AI agents have been endowed with anthropomorphic traits, such as a human-like appearance, in prior studies to improve human trust in AI, it is still an open question whether humans have more trust in an AI teammate and achieve better human-AI joint performance if they are deceived about the identity of their AI teammate as another human. This research assesses the effects of teammate identity (“human” vs. AI) and teammate performance (low-performing vs. high-performing AI) on human-AI cooperation through a human subjects study. The results of this study show that humans behaviorally trust the AI more than another human by accepting their AI teammate's decisions more often. In addition, teammate performance has a significant effect on human-AI joint performance in the study, while teammate identity does not. These results caution against deceiving humans about the identity of AI in future applications involving human-AI cooperation.

High-Accuracy Driving Control of a Stone-Throwing Mobile Robot for Curling

In this study, a novel mobile robot that can throw precisely a stone in a curling match is introduced. This mobile robot plays alongside a human team. Several requirements for developing the mobile robot are defined so that it follows the game rules and operates on an ice field. A static force analysis considering the operating conditions of the mobile robot is conducted to derive the required motor torque and the optimal mechanical design. For a successful stone-throwing, the mobile robot must present a high driving performance on an ice surface with a target velocity and an angle provided by an autonomous strategy generator. To achieve the target velocity on an icy surface, a velocity control algorithm based on slip ratio control (SRC) is proposed. Moreover, to precisely achieve heading angle control, a heading angle controller including a steering angle disturbance observer (SA-DOB) is introduced. The mathematical model of the SA-DOB is derived by a dynamic analysis of the mobile robot. Several experimental results verify the proposed motion control algorithm and the feasibility of the mobile robot as a curling robot to compete with a human team. This study is motivated by the challenge of driving a mobile robot on an extremely slippery surface with high-accuracy motion for curling. To prevent slippage, a slip ratio controller is adopted based on the difference between the wheel and robot speeds. To maintain a desired heading angle of the mobile robot during driving, orientation control based on the yaw dynamics is developed. Moreover, the robot does not require any positioning information from external sources, such as sensors and cameras. In addition to playing an actual game, this curling robot can be utilized for training athletes. Furthermore, the developed algorithms for high-accuracy driving on ice in an indoor stadium can be applied to various mobile robots that drive on other slippery environments (such as sand and dust) and sealed spaces (such as underground warehouses) where external positioning signals cannot be received. The proposed robot is limited to straight driving, and the possibility of extending it to circular motion is still under development. Note to Practitioners—This study is motivated by the challenge of driving a mobile robot on an extremely slippery surface with high-accuracy motion for curling. To prevent slippage, a slip ratio controller is adopted based on the difference between the wheel and robot speeds. To maintain a desired heading angle of the mobile robot during driving, orientation control based on the yaw dynamics is developed. Moreover, the robot does not require any positioning information from external sources, such as sensors and cameras. In addition to playing an actual game, this curling robot can be utilized for training athletes. Furthermore, the developed algorithms for high-accuracy driving on ice in an indoor stadium can be applied to various mobile robots that drive on other slippery environments (such as sand and dust) and sealed spaces (such as underground warehouses) where external positioning signals cannot be received. The proposed robot is limited to straight driving, and the possibility of extending it to circular motion is still under development.

Multimodal collaborative brain-computer interfaces aid human-machine team decision-making in a pandemic scenario

Objective. Critical decisions are made by effective teams that are characterized by individuals who trust each other and know how to best integrate their opinions. Here, we introduce a multimodal brain-computer interface (BCI) to help collaborative teams of humans and an artificial agent achieve more accurate decisions in assessing danger zones during a pandemic scenario. Approach. Using high-resolution simultaneous electroencephalography/functional MRI (EEG/fMRI), we first disentangled the neural markers of decision-making confidence and trust and then employed machine-learning to decode these neural signatures for BCI-augmented team decision-making. We assessed the benefits of BCI on the team’s decision-making process compared to the performance of teams of different sizes using the standard majority or weighing individual decisions. Main results. We showed that BCI-assisted teams are significantly more accurate in their decisions than traditional teams, as the BCI is capable of capturing distinct neural correlates of confidence on a trial-by-trial basis. Accuracy and subjective confidence in the context of collaborative BCI engaged parallel, spatially distributed, and temporally distinct neural circuits, with the former being focused on incorporating perceptual information processing and the latter involving action planning and executive operations during decision making. Among these, the superior parietal lobule emerged as a pivotal region that flexibly modulated its activity and engaged premotor, prefrontal, visual, and subcortical areas for shared spatial-temporal control of confidence and trust during decision-making. Significance. Multimodal, collaborative BCIs that assist human-artificial agent teams may be utilized in critical settings for augmented and optimized decision-making strategies.

Common belief multi-agent reinforcement learning based on variational recurrent models

The tacit cooperation among human teams benefits from the fact that consensus can be reached on a task through common belief. Similar to human social groups, agents in distributed learning systems can also rely on common belief to achieve cooperation under the condition of limited communication. In this paper, we show the role of common belief among agents in completing cooperative tasks, by proposing the Common Belief Multi-Agent (CBMA) reinforcement learning method. CBMA is a novel value-based method that infers the belief between agents with a variational model and models the environment with a variational recurrent neural network. We validate CBMA on two grid-world games as well as the StarCraft II micromanagement benchmark. Experimental results show that the learned common belief by CBMA can improve performance in both discrete and continuous state settings.

The cyclical ethical effects of using artificial intelligence in education.

Our synthetic review of the relevant and related literatures on the ethics and effects of using AI in education reveals five qualitatively distinct and interrelated divides associated with access, representation, algorithms, interpretations, and citizenship. We open our analysis by probing the ethical effects of algorithms and how teams of humans can plan for and mitigate bias when using AI tools and techniques to model and inform instructional decisions and predict learning outcomes. We then analyze the upstream divides that feed into and fuel the algorithmic divide, first investigating access (who does and does not have access to the hardware, software, and connectivity necessary to engage with AI-enhanced digital learning tools and platforms) and then representation (the factors making data either representative of the total population or over-representative of a subpopulation’s preferences, thereby preventing objectivity and biasing understandings and outcomes). After that, we analyze the divides that are downstream of the algorithmic divide associated with interpretation (how learners, educators, and others understand the outputs of algorithms and use them to make decisions) and citizenship (how the other divides accumulate to impact interpretations of data by learners, educators, and others, in turn influencing behaviors and, over time, skills, culture, economic, health, and civic outcomes). At present, lacking ongoing reflection and action by learners, educators, educational leaders, designers, scholars, and policymakers, the five divides collectively create a vicious cycle and perpetuate structural biases in teaching and learning. However, increasing human responsibility and control over these divides can create a virtuous cycle that improves diversity, equity, and inclusion in education. We conclude the article by looking forward and discussing ways to increase educational opportunity and effectiveness for all by mitigating bias through a cycle of progressive improvement.

Understanding Human Decision Processes: Inferring Decision Strategies From Behavioral Data

This work investigates a method to infer and classify decision strategies from human behavior, with the goal of improving human-agent team performance by providing AI-based decision support systems with knowledge about their human teammate. First, an experiment was designed to mimic a realistic emergency preparedness scenario in which the test participants were tasked with allocating resources into 1 of 100 possible locations based on a variety of dynamic visual heat maps. Simple participant behavioral data, such as the frequency and duration of information access, were recorded in real time for each participant. The data were examined using a partial least squares regression to identify the participants’ likely decision strategy, that is, which heat maps they relied upon the most. The behavioral data were then used to train a random forest classifier, which was shown to be highly accurate in classifying the decision strategy of new participants. This approach presents an opportunity to give AI systems the ability to accurately model the human decision-making process in real time, enabling the creation of proactive decision support systems and improving overall human-agent teaming.

A Holistic Approach for Role Inference and Action Anticipation in Human Teams

The ability to anticipate human actions is critical to many cyber-physical systems, such as robots and autonomous vehicles. Computer vision and sensing algorithms to date have focused on extracting and predicting visual features that are explicit in the scene, such as color, appearance, actions, positions, and velocities, using video and physical measurements, such as object depth and motion. Human actions, however, are intrinsically influenced and motivated by many implicit factors such as context, human roles and interactions, past experience, and inner goals or intentions. For example, in a sport team, the team strategy, player role, and dynamic circumstances driven by the behavior of the opponents, all influence the actions of each player. This article proposes a holistic framework for incorporating visual features, as well as hidden information, such as social roles, and domain knowledge. The approach, relying on a novel dynamic Markov random field (DMRF) model, infers the instantaneous team strategy and, subsequently, the players’ roles that are temporally evolving throughout the game. The results from the DMRF inference stage are then integrated with instantaneous visual features, such as individual actions and position, in order to perform holistic action anticipation using a multi-layer perceptron (MLP). The approach is demonstrated on the team sport of volleyball, by first training the DMRF and MLP offline with past videos, and, then, by applying them to new volleyball videos online. These results show that the method is able to infer the players’ roles with an average accuracy of 86.99%, and anticipate future actions over a sequence of up to 46 frames with an average accuracy of 80.50%. Additionally, the method predicts the onset and duration of each action achieving a mean relative error of 14.57% and 15.67%, respectively.

Explanations and trust: What happens to trust when a robot partner does something unexpected?

Performance within Human-Autonomy Teams (HATs) is influenced by the effectiveness of communication between humans and robots. Communication is particularly important when robot teammates engage in behaviors that were not anticipated by the human teammate which could degrade trust. However, the literature on trust repair focuses on the role of apologies which may not be appropriate for an unexpected behavior since this behavior may not be an error. Explanations are one method that can be used by robot teammates to avoid costly trust degradation when human expectations are violated. The current study used an Urban Search and Rescue (USAR) scenario to examine the role of explanation in a context wherein a robot teammate deviated from an expected behavior. The current study examined how trust, trustworthiness, and responsibility attribution were influenced by observing the robot teammate deviate from an expected behavior. Participants (N = 148) used an online platform to view videos of the robot: 1) following a planned search path, and 2) deviating from a planned search path. A debriefing event between the human and the robot followed each search activity. Four explanation conditions were tested in the debriefing phase following the behavioral violation. Results showed that trust and trustworthiness (ability, benevolence, and integrity) declined following the unexpected behavior. Accordingly, responsibility attribution shifted from the human to the robot following the unexpected behavior. Explanation strategies that focused on communicating why the event occurred by highlighting the robot's environmental awareness were most effective at buffering the decline in trust and trustworthiness.

Designing for Mutually Beneficial Decision Making in Human-Agent Teaming

This paper presents a joint decision-making framework between human and artificial intelligent agents in an effort to create a cohesive team uninhibited by each other’s actions. Based on the well-known Recognition Primed Decision-Making Model, our framework expands upon RPD’s single decision maker to be more Human-Agent Teaming (HAT) oriented. Specifically, our framework includes three layers of shared cognition to ensure both a consistent level of transparency between members and the efficient completion of the task. The first layer provides itself as a foundation of expectations that provides familiarity recognition in a situation. The second layer categorizes the environmental features into relevant decisions informing the symbiotic nature of who should and how to enact decisions collaboratively, which is the third layer. Altogether, this mutually beneficial decision-making model emphasizes transparency so that both humans and artificial agents are equal partners in completing tasks in unique situations.

Effects of Context, Assistance, and Communication on Beliefs About Cooperation in Human-Machine Teaming

The efficacy of future human-machine teaming will be determined by the ability of machine agents to engage in teamwork behaviors and processes with their human teammates. A critical aspect of teamwork is cooperation, as team members must work interdependently to achieve common goals. In the current experiment we investigated how violations of cooperation expectations, presented to participants in a narrative vignette, influenced ratings of cooperation on a novel measure derived from social interdependence theory. Our results indicated that participants’ ratings of cooperation were strongly influenced by actions associated with assisting and communicating with a cooperating partner; violations in these expectations resulted in much lower estimates of cooperation, though the identity of the actors as two humans or a human and a robot did not appear to matter. Overall, this is an important first step to understanding the factors that influence perceptions of cooperation in human-machine teaming.

Measurements of Mental Stress and Safety Awareness during Human Robot Collaboration -Review

Human-robot collaboration is an emerging research area that has gained tremendous attention in both academia and industry. Yet, the feature that human and robot sharing the workplace has led to safety concerns. In particular, the psychological states of human teammates during human-robot collaboration remains unclear but is also of great importance to workplace safety. This manuscript briefly reviewed possible direct and indirect measures that can be used to evaluate workers’ mental stress and safety awareness during human robot collaboration. It was concluded that each measure reviewed in this paper has its validity and rationality, and a combination of different methods may provide a more comprehensive and accurate assessment.

Use of cyber attack and defense agents in cyber ranges: A case study

With the ever-changing cybersecurity landscape, the need for a continuous training for new cybersecurity skill sets is a requirement. Such continuous training programs can be delivered on platforms like cyber ranges. Cyber ranges support training by providing a simulated or emulated representation of a computer network infrastructure, besides additional training and testing services. Cyber attack and defense skills can be gained by attacking and defending a simulated or an emulated infrastructure. However, to provide a realistic training in such infrastructures, there is a need for necessary friction in the environment. Human teams, playing both attackers’ and defenders’ roles, provide this friction. Involving human teams in large-scale cybersecurity exercises is relatively inefficient and not feasible for standardizing training because different teams apply different tactics. Currently, the proposed solutions for cyber range training platforms focus on automating the deployment of the cybersecurity exercise infrastructure but not on the execution part. This leaves a room for improving exercise execution by adding realism and efficiency. This research presents an agent-based system that emulates cyber attack and defense actions during cybersecurity exercise execution; this helps provide realistic and efficient cybersecurity training. To specify agents’ behavior and decision making, a new formal model, called the execution plan (EP), was developed and utilized in this work.

Adapt and overcome: Perceptions of adaptive autonomous agents for human-AI teaming

Rapid advances in AI technologies have caused teams to explore the use of AI agents as full, active members of the team. The complex environments that teams occupy require human team members to constantly adapt their behaviors, and thus the ability of AI teammates to similarly adapt to changing situations significantly enhances the team’s chances to succeed. In order to design such agents, it is important that we understand not only how to identify the amount of autonomous control AI agents have over their decisions, but also how changes to this control cognitively affects the rest of the team. Professional organizations often break their work cycles into phases that set limits on the team members’ actions, and we propose that a similar process could be used to define the autonomy levels of AI teammates. Cyber incident response is an ideal context for this proposal, as we were able to use incident response phases to explore how a team’s work cycle could guide an AI agent’s changing level of autonomy. Using a mixed methods approach, we recruited 103 participants to complete a factorial survey containing ten contextual vignettes focused on an AI teammate’s level of autonomy in incident response contexts, and from these participants we conducted twenty-two follow-on qualitative interviews that further explored how the participants felt an AI agent’s adaptive capabilities would affect team performance and cohesiveness. Our results showed that work cycles can be used to assign autonomy levels to adaptive AI agents based upon the degree of formal processes and predictability of the team’s tasks during the cycle, and that dynamic, human-like adaptation methods are vital to effective human-AI teams. This research provides significant contributions to the HCI community by proposing design recommendations for the development of adaptive autonomous teammates that both enhance Human-AI teams’ productivity and promote positive team dynamics.

The role of entrepreneurial skills as a vehicle for business growth: a study in Spanish start-ups

PurposeBusiness growth is one of the most studied areas over the years. However, with the current uncertainty and entrepreneurial dynamism it becomes relevant to consider new variables such as entrepreneurial skills and competencies that influence its development. Accordingly, this research refers to the impact that the individual's skills have on the entrepreneurial environment. For this purpose, a survey has been developed of employees of different organizations considering the variables of high degree of proactivity in the employees' attitude, entrepreneurial training, innovation, previous experience or risk aversion.Design/methodology/approachThe research has been conducted through fuzzy set qualitative comparative analysis (fsQCA) and the result shows the differences between the combination of variables for business growth through the consideration of sales growth and profit.FindingsThe results of this research provide new insights that allow the development and boosting of business growth.Originality/valueThe main contribution of this work is to pay attention to the human team of startups and show the role that this has in their growth.