When robots interact with human partners, often these partners change their behavior in response to the robot. On the one hand this is challenging because the robot must learn to coordinate with a dynamic partner. But on the other hand -- if the robot understands these dynamics -- it can harness its own behavior, influence the human, and guide the team towards effective collaboration. Prior research enables robots to learn to influence other robots or simulated agents. In this paper we extend these learning approaches to now influence humans. What makes humans especially hard to influence is that -- not only do humans react to the robot -- but the way a single user reacts to the robot may change over time, and different humans will respond to the same robot behavior in different ways. We therefore propose a robust approach that learns to influence changing partner dynamics. Our method first trains with a set of partners across repeated interactions, and learns to predict the current partner's behavior based on the previous states, actions, and rewards. Next, we rapidly adapt to new partners by sampling trajectories the robot learned with the original partners, and then leveraging those existing behaviors to influence the new partner dynamics. We compare our resulting algorithm to state-of-the-art baselines across simulated environments and a user study where the robot and participants collaborate to build towers. We find that our approach outperforms the alternatives, even when the partner follows new or unexpected dynamics. Videos of the user study are available here: https://youtu.be/lYsWM8An18g

Swarm robotic systems are distributed systems wherein a set of robots cooperatively perform a task, without any centralized coordination [29]. Although individual robots are governed by relatively simple reactive controllers, interactions within the swarm may give rise to complex behaviors that were not explicitly programmed. Ultimately, these behaviors enable the swarm to achieve goals that would defy each single robot in isolation, or would require more expensive robots to achieve the same goals as effectively as the swarm does - see, e.g, [4, 33] for some examples. While understanding individual robot behavior is easy, predicting the overall swarm behavior is difficult, and thus engineering controllers for individual robots that will guarantee a desired swarm behavior is not a straightforward task. Traditionally, the analysis of swarms is carried out either by testing real robot implementations, or by computational simulations [20, 22]; however, these approaches provide little guarantees as they suffer from intrinsically incomplete coverage. As suggested by many authors, higher levels of assurance in swarm behavior can be obtained via formal methods [32, 30, 16, 5, 18, 23].

In order to guide the multi-agent system in a cluttered environment, a connected quadrangle virtual tube is designed for all agents to keep moving within it, whose basis is called the single trapezoid virtual tube. There is no obstacle inside the tube, namely the area inside the tube can be seen as a safety zone. Then, a distributed swarm controller is proposed for the single trapezoid virtual tube passing problem. This issue is resolved by a gradient vector field method with no local minima. Formal analyses and proofs are made to show that all agents are able to pass the single trapezoid virtual tube. Finally, a modified controller is put forward for convenience in practical use. For the connected quadrangle virtual tube, a modified switching logic is proposed to avoid the deadlock and prevent agents from moving outside the virtual tube. Finally, the effectiveness of the proposed method is validated by numerical simulations and real experiments.

It has been experimentally shown that communities in social networks tend to have a core-periphery topology. However, there is still a limited understanding of the precise structure of core-periphery communities in social networks including the connectivity structure and interaction rates between agents. In this paper, we use a game-theoretic approach to derive a more precise characterization of the structure of core-periphery communities.

An open question in the study of emergent behaviour in multi-agent Bayesian systems is the relationship, if any, between individual and collective inference. In this paper we explore the correspondence between generative models that exist at two distinct scales, using spin glass models as a sandbox system to investigate this question. We show that the collective dynamics of a specific type of active inference agent is equivalent to sampling from the stationary distribution of a spin glass system. A collective of specifically-designed active inference agents can thus be described as implementing a form of sampling-based inference (namely, from a Boltzmann machine) at the higher level. However, this equivalence is very fragile, breaking upon simple modifications to the generative models of the individual agents or the nature of their interactions. We discuss the implications of this correspondence and its fragility for the study of multiscale systems composed of Bayesian agents.

The safety of single-vehicle autonomous driving technology is limited due to the limits of perception capability of on-board sensors. In contrast, vehicle-road collaboration technology can overcome those limits and improve the traffic safety and efficiency, by expanding the sensing range, improving the perception accuracy, and reducing the response time. However, such a technology is still under development; it requires rigorous testing and verification methods to ensure the reliability and trustworthiness of the technology. In this thesis, we focus on three major tasks: (1) analyze the functional characteristics related to the scenarios of vehicle-road cooperations, highlightening the differences between vehicle-road cooperative systems and traditional single-vehicle autonomous driving systems; (2) refine and classifiy the functional characteristics of vehicle-road cooperative systems; (3) design and develop a simulation system, and provide a visual interface to facilitate development and analysis. The efficiency and effectiveness the proposed method are verfied by experiments.

Through a series of federal initiatives and orders, the U.S. Government has been making a concerted effort to ensure American leadership in AI. These broad strategy documents have influenced organizations such as the United States Department of the Air Force (DAF). The DAF-MIT AI Accelerator is an initiative between the DAF and MIT to bridge the gap between AI researchers and DAF mission requirements. Several projects supported by the DAF-MIT AI Accelerator are developing public challenge problems that address numerous Federal AI research priorities. These challenges target priorities by making large, AI-ready datasets publicly available, incentivizing open-source solutions, and creating a demand signal for dual use technologies that can stimulate further research. In this article, we describe these public challenges being developed and how their application contributes to scientific advances.

Human behaviour is complex and nuanced. Consider how an act as simple as purchasing a cup of coffee involves an intricate spatio-temporal sequence of actions and perception: instructions, clarifications, and feedback weave across language, touch, and visual communicative cues, with the precise timing of each providing yet more information to our interactive partners. If we ever hope to create artificial agents that can participate in similar interactions, we must develop effective ways to evaluate their behaviour in naturalistic settings with humans. One obvious approach to evaluating interactive agent behaviour is to leverage a human's judgement during the course of their interaction with an agent. However, this requires a high human cost, both in number of human participants required and in total number of human hours spent, and has no straightforward mechanism to control for human behavioural diversity. The latter problem in particular can result in highly variable metrics if human behaviour is too noisy, or imprecise metrics if human behaviour is not diverse enough. Human behavior is also non-stationary over time, as it can be subtly impacted by agent performance, causing drift. Thus, despite being a "gold standard", the opacity of the online human-agent evaluation setting makes any generated metrics difficult to interpret and communicate, and hence, difficult to optimize for. Researchers therefore typically rely on other methods of evaluation, such as validation performance of the agent's optimized objective (e.g.

The standard problem setting in cooperative multi-agent settings is self-play (SP), where the goal is to train a team of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions ("handshakes") and are not compatible with other, independently trained agents or humans. This latter desiderata was recently formalized by Hu et al. 2020 as the zero-shot coordination (ZSC) setting and partially addressed with their Other-Play (OP) algorithm, which showed improved ZSC and human-AI performance in the card game Hanabi. OP assumes access to the symmetries of the environment and prevents agents from breaking these in a mutually incompatible way during training. However, as the authors point out, discovering symmetries for a given environment is a computationally hard problem. Instead, we show that through a simple adaption of k-level reasoning (KLR) Costa Gomes et al. 2006, synchronously training all levels, we can obtain competitive ZSC and ad-hoc teamplay performance in Hanabi, including when paired with a human-like proxy bot. We also introduce a new method, synchronous-k-level reasoning with a best response (SyKLRBR), which further improves performance on our synchronous KLR by co-training a best response.

A schema-guided approach to dialogue management has been shown in recent work to be effective in creating robust customizable virtual agents capable of acting as friendly peers or task assistants. However, successful applications of these methods in open-ended, mixed-initiative domains remain elusive -- particularly within medical domains such as virtual standardized patients, where such complex interactions are commonplace -- and require more extensive and flexible dialogue management capabilities than previous systems provide. In this paper, we describe a general-purpose schema-guided dialogue management framework used to develop SOPHIE, a virtual standardized cancer patient that allows a doctor to conveniently practice for interactions with patients. We conduct a crowdsourced evaluation of conversations between medical students and SOPHIE. Our agent is judged to produce responses that are natural, emotionally appropriate, and consistent with her role as a cancer patient. Furthermore, it significantly outperforms an end-to-end neural model fine-tuned on a human standardized patient corpus, attesting to the advantages of a schema-guided approach.