Human-Robot Teamwork during Disaster Response

Human collaborator’s workload plays a central role in human-robot collaboration. Algorithms designed to minimize cognitive workload enhance fluent human-robot teamwork. Time series data of workload is vital for both designing and assessing these algorithms. However, accurately quantifying and measuring cognitive workload, particularly at high temporal resolution, poses a substantial challenge. Towards addressing this challenge, we explore the potential of after-action reviews (AARs) as a tool for gauging workload during human-robot collaboration. First, through a case study, we present and demonstrate AutoAAR for measuring human workload post-task at a high temporal resolution. Second, through a user study, we quantify the validity and utility of measurements derived using AutoAAR for human-robot teamwork.The paper concludes with guidelines and future directions to extend this method to measure other internal states, such as trust and intent.

To forge effective collaborations with humans, robots require the capacity to understand and predict the behaviors of their human counterparts. There is a growing body of computational research on human modeling for human-robot interaction (HRI). However, a key bottleneck in conducting this research is the relative lack of data of human internal states – like intent, workload, and trust – which undeniably affect human behavior. Despite their significance, these states are elusive to measure, making the assembly of datasets a challenge and hindering the progression of human modeling techniques. To help address this, we first introduce Rescue World for Teams (RW4T): a configurable testbed to simulate disaster response scenarios requiring human-robot collaboration. Next, using RW4T, we curate a multimodal dataset of human-robot behavior and internal states in dyadic human-robot collaboration. This RW4T dataset includes state, action and reward sequences, and all the necessary data to replay a visual task execution. It further contains psychophysiological metrics like heart rate and pupillometry, complemented by self-reported cognitive state measures. With data from 20 participants, each undertaking five human-robot collaborative tasks, this dataset accompanied with the simulator can serve as a valuable benchmark for human behavior modeling.

Effective human-human and human-autonomy teamwork is critical but often challenging to perfect. The challenge is particularly relevant in time-critical domains, such as healthcare and disaster response, where the time pressures can make coordination increasingly difficult to achieve and the consequences of imperfect coordination can be severe. To improve teamwork in these and other domains, we present TIC: an automated intervention approach for improving coordination between team members. Using BTIL, a multi-agent imitation learning algorithm, our approach first learns a generative model of team behavior from past task execution data. Next, it utilizes the learned generative model and team’s task objective (shared reward) to algorithmically generate execution-time interventions. We evaluate our approach in synthetic multi-agent teaming scenarios, where team members make decentralized decisions without full observability of the environment. The experiments demonstrate that the automated interventions can successfully improve team performance and shed light on the design of autonomous agents for improving teamwork.

We present Bayesian Team Imitation Learner (BTIL), an imitation learning algorithm to model the behavior of teams performing sequential tasks in Markovian domains. In contrast to existing multi-agent imitation learning techniques, BTIL explicitly models and infers the time-varying mental states of team members, thereby enabling learning of decentralized team policies from demonstrations of suboptimal teamwork. Further, to allow for sample- and label-efficient policy learning from small datasets, BTIL employs a Bayesian perspective and is capable of learning from semi-supervised demonstrations. We demonstrate and benchmark the performance of BTIL on synthetic multi-agent tasks as well as a novel dataset of human-agent teamwork. Our experiments show that BTIL can successfully learn team policies from demonstrations despite the influence of team members’ (time-varying and potentially misaligned) mental states on their behavior.

Autonomous agents operating in the real world often need to interact with other agents to accomplish their tasks. For such agents, the ability to model behavior of other agents – both human and artificial – without complete knowledge of their decision factors is essential. Towards realizing this ability, we present Factorial Agent Markov Model (FAMM), a model to represent behavior of other agents performing sequential tasks. In contrast with most existing models, FAMM allows for behavior of other agents to depend on multiple, time-varying latent decision factors and does not assume rationality. To enable learning of \famm parameters by observing behavior of other agents, we provide a set of variational inference algorithms for the unsupervised, semi-supervised, and supervised settings. These Bayesian learning algorithms for the FAMM enable agents to model other agents using execution traces and domain-specific priors. We demonstrate the utility of FAMM and corresponding learning algorithms using three synthetic domains and benchmark them against existing algorithms for modeling agent behavior. Our numerical experiments demonstrate that, despite the presence of multiple and time-varying latent states, our approach is capable of learning predictive models of other agents with semi-supervision.

Autonomous agents are increasingly being deployed amongst human end-users. Yet, human users often have little knowledge of how these agents work or what they will do next. This lack of transparency has already resulted in unintended consequences during AI use: a concerning trend which is projected to increase with the proliferation of autonomous agents. To curb this trend and ensure safe use of AI, assisting users in establishing an accurate understanding of agents that they work with is essential. In this work, we present AI teacher, a user-centered Explainable AI framework to address this need for autonomous agents that follow a Markovian policy. Our framework first computes salient instructions of agent behavior by estimating a user’s mental model and utilizing algorithms for sequential decision-making. Next, in contrast to existing solutions, these instructions are presented interactively to the end-users, thereby enabling a personalized approach to improving AI transparency. We evaluate our framework, with emphasis on its interactive features, through experiments with human participants. The experiment results suggest that, relative to non-interactive approaches, interactive teaching can both reduce the amount of time it takes for humans to create accurate mental models of these agents and is subjectively preferred by human users.