High-stress environments, such as first-response or a NASA control room, require optimal task performance, as a single mistake may cause monetary loss or even the loss of human life. Robots can partner with humans in a collaborative or supervisory paradigm to augment the human’s abilities and increase task performance. Such teaming paradigms require the robot to appropriately interact with the human without decreasing either’s task performance. Workload is related to task performance; thus, a robot may use a human’s workload state to modify its interactions with the human. Assessing the human’s workload state may also allow for dynamic task (re-)allocation, as a robot can predict whether a task may overload the human and, if so, allocate it elsewhere. A diagnostic workload assessment algorithm that accurately estimates workload using results from two evaluations, one peer based and one supervisory based, is presented. The algorithm correctly classified workload at least 90% of the time when trained on data from the same human--robot teaming paradigm. This algorithm is an initial step toward robots that can adapt their interactions and intelligently (re-)allocate tasks.

Supervisory control environments, such as the NASA control room can induce high workload levels in situations where a single error is capable of costing millions of dollars. An intelligent system can improve human supervisor performance by monitoring the human's workload levels and intelligently adapting the system capabilities, such as adapting the interaction medium or reallocating roles and responsibilities between the human and the system. Systems capable of responding promptly and accurately to the human's changes in workload require a workload assessment algorithm that can detect changes to all components of workload in real time. A review of 24 workload assessment algorithms across six task domains is provided. Each algorithm is reviewed based on four criteria: sensitivity, diagnosticity, suitability, and generalizability. The majority of the reviewed algorithms were developed for a specific task domain and are unable to generalize different tasks. Further, the majority of the algorithms do not account for individual differences, only assess one or two workload components, and do not classify underload.

Reaction time and response time have been successfully measured in laboratory settings. As robots move into the real-world, such metrics are needed for human-robot team deployments when evaluating interaction naturalness, ability to maintain safety, and task performance. Potential real-world reaction and response time metrics for peer-based teams are presented. Primary and secondary task reaction and response times were measured via video and auditory coding for a subset of first response tasks. The successful application of the metrics showed that primary task reaction and response times were longer for human-robot teams.

Mass casualty events caused by a biological weapon require fully capable first response teams. However, human first responders are equipped with protective gear, which limits their capabilities to complete tasks. Robots can be employed to work collaboratively with the first responders in order to augment the human's reduced abilities. The robot needs to understand and adapt to the human's workload level in order for the human-machine team to effectively complete tasks. The automatic detection of human workload levels can provide valuable insight into the human's capabilities, as workload has a direct relationship with task performance. The robot can monitor the objective metrics of the human's workload level in order to accurately estimate workload via a workload assessment algorithm. The algorithm must be able to assess overall workload and the components of workload, in order for the robot to correctly adapt its interactions or reallocate tasks among the team. A novel workload assessment algorithm that provides an accurate estimate of overall workload and each workload component is presented and evaluated. The algorithm is capable of distinguishing between high and low workload conditions; however, the algorithm's workload values correlate poorly to a generated workload model. Modifications to enhance the algorithm's capabilities are discussed and will be investigated in future work.

Successful human-robot (H-R) teams working with direct interaction and close coupling will have relationships that vary, depending on whether or not collaboration is prioritized and how collaboration changes the human mental workload and the team's task performance. Modeling of representative functions can provide predictions of changes in mental workload and the potential impact on team performance. The presented research focuses on modeling and quantifying mental workload for H-R teams in which team members have some individually assigned responsibilities but must also make joint decisions with a teammate. IMPRINT Pro, a discrete event simulation modeling tool created by the U.S. Army Research Laboratory, was used to model human-human (H-H) and H-R teams completing a reconnaissance task in a building. This research evaluated H-H and H-R teams completing the same reconnaissance tasks. Predictions of mental-workload levels from the model and the evaluation results showed that mental workload was lower for the H-R teams. The results for the closely coupled teams were compared to results from a prior evaluation with a master-slave relationship; similar results were found for both evaluations. Mental workload was lower in H-R teams than in H-H teams, but task performance did not differ between the two.

When people interact with intelligent agents, they likely rely upon a wide range of existing knowledge about machines, minds, and intelligence. This knowledge not only guides these interactions, but it can be challenged and potentially changed by interaction experiences. We hypothesized that a key factor mediating conceptual change in response to human-machine interactions is cognitive conflict, or dissonance. In this experiment, we evaluated whether interactions with a robot partner during a realistic medical triage scenario caused increased levels of cognitive dissonance relative to a control condition in which the same task was performed with a human partner. In addition, we evaluated whether heightened levels of dissonance affected concepts about agents. We observed increased cognitive dissonance after the human-robot interaction and found that this dissonance was correlated with a significantly less intentional (e.g., less human-like) view of the intelligence inherent to computers.

The effect of a robotic teammate on a human partner's workload has not been fully quantified. Prior research found that human participants experienced lower workload when working with a robotic partner than when working with a human partner. An evaluation investigated whether a similar trend in workload exists for tasks requiring direct and collaborative interaction between the partners, and joint team decision-making. The subjective results indicate a similar trend to the prior results; participants rated workload lower for the more complex task when partnered with a robot than when partnered with a human.

Clips from an evaluation where participants, each paired with either a human or robot partner, were deployed to search a hallway for suspicious items, in a manner similar to tactics used by first responders handling bomb threats are presented. The teams used natural, verbal communication to collaborate, determine where hazards were located, and which items were suspicious. The video demonstrates that the investigations in both conditions played out in a similar manner and participants were able to complete the investigations successfully with a robot partner; however, sometimes the participants were uncertain how to interact with the robot.

Human-Robot peer-based teams are evolving from a far-off possibility into a reality. Human Performance Moderator Functions (HPMFs) can be used to predict human behavior by incorporating the effects of internal and external influences such as fatigue and workload. The applicability of HPMFs to human-robot teams is not proven. The presented research focuses on determining the applicability of workload HPMFs in team tasks for first response mass casualty triage incidents between a Human-Human and a Human-Robot team. A model representing workload for each team was developed using IMPRINT Pro. The results from an empirical evaluation were compared to the model results. While significant differences between the two conditions were not found in all data, there was a general trend that workload in the human-robot condition was slightly lower than the workload experienced in the human-human condition. This trend was predicted by the IMPRINT Pro models. These results are the first to indicate that existing HPMFs can be applied to human-robot peer-based teams.

Interaction between humans and robots in peer-based teams can be dramatically affected by human performance. Our research is focused on determining if existing human performance moderator functions apply to peer-based human-robot interaction and if not, how such functions must be modified. Our initial work focuses on modeling workload. Validation of the models will require human subject evaluations. Future work will incorporate larger numbers of performance moderator functions and will apply the results to distributing tasks to team members.