This paper addresses the efficient management of Mobile Access Points (MAPs), which are Unmanned Aerial Vehicles (UAV), in 5G networks. We propose a two-level hierarchical architecture, which dynamically reconfigures the network while considering Integrated Access-Backhaul (IAB) constraints. The high-layer decision process determines the number of MAPs through consensus, and we develop a joint optimization process to account for co-dependence in network self-management. In the low-layer, MAPs manage their placement using a double-attention based Deep Reinforcement Learning (DRL) model that encourages cooperation without retraining. To improve generalization and reduce complexity, we propose a federated mechanism for training and sharing one placement model for every MAP in the low-layer. Additionally, we jointly optimize the placement and backhaul connectivity of MAPs using a multi-objective reward function, considering the impact of varying MAP placement on wireless backhaul connectivity.

We consider the problem of evaluating forecasts of binary events whose predictions are consumed by rational agents who take an action in response to a prediction, but whose utility is unknown to the forecaster. We show that optimizing forecasts for a single scoring rule (e.g., the Brier score) cannot guarantee low regret for all possible agents. In contrast, forecasts that are well-calibrated guarantee that all agents incur sublinear regret. However, calibration is not a necessary criterion here (it is possible for miscalibrated forecasts to provide good regret guarantees for all possible agents), and calibrated forecasting procedures have provably worse convergence rates than forecasting procedures targeting a single scoring rule. Motivated by this, we present a new metric for evaluating forecasts that we call U-calibration, equal to the maximal regret of the sequence of forecasts when evaluated under any bounded scoring rule. We show that sublinear U-calibration error is a necessary and sufficient condition for all agents to achieve sublinear regret guarantees. We additionally demonstrate how to compute the U-calibration error efficiently and provide an online algorithm that achieves $O(\sqrt{T})$ U-calibration error (on par with optimal rates for optimizing for a single scoring rule, and bypassing lower bounds for the traditionally calibrated learning procedures). Finally, we discuss generalizations to the multiclass prediction setting.

Parallel self-assembly is an efficient approach to accelerate the assembly process for modular robots. However, these approaches cannot accommodate complicated environments with obstacles, which restricts their applications. This paper considers the surrounding stationary obstacles and proposes a parallel self-assembly planning algorithm named SAPOA. With this algorithm, modular robots can avoid immovable obstacles when performing docking actions, which adapts the parallel self-assembly process to complex scenes. To validate the efficiency and scalability, we have designed 25 distinct grid maps with different obstacle configurations to simulate the algorithm. From the results compared to the existing parallel self-assembly algorithms, our algorithm shows a significantly higher success rate, which is more than 80%. For verification in real-world applications, a multi-agent hardware testbed system is developed. The algorithm is successfully deployed on four omnidirectional unmanned surface vehicles, CuBoats. The navigation strategy that translates the discrete planner, SAPOA, to the continuous controller on the CuBoats is presented. The algorithm's feasibility and flexibility were demonstrated through successful self-assembly experiments on 5 maps with varying obstacle configurations.

Deploying service robots in our daily life, whether in restaurants, warehouses or hospitals, calls for the need to reason on the interactions happening in dense and dynamic scenes. In this paper, we present and benchmark three new approaches to model and predict multi-agent interactions in dense scenes, including the use of an intuitive qualitative representation. The proposed solutions take into account static and dynamic context to predict individual interactions. They exploit an input- and a temporal-attention mechanism, and are tested on medium and long-term time horizons. The first two approaches integrate different relations from the so-called Qualitative Trajectory Calculus (QTC) within a state-of-the-art deep neural network to create a symbol-driven neural architecture for predicting spatial interactions. The third approach implements a purely data-driven network for motion prediction, the output of which is post-processed to predict QTC spatial interactions. Experimental results on a popular robot dataset of challenging crowded scenarios show that the purely data-driven prediction approach generally outperforms the other two. The three approaches were further evaluated on a different but related human scenarios to assess their generalisation capability.

Agent-based modeling (ABM) and simulation have emerged as important tools for studying emergent behaviors, especially in the context of swarming algorithms for robotic systems. Despite significant research in this area, there is a lack of standardized simulation environments, which hinders the development and deployment of real-world robotic swarms. To address this issue, we present Zespol, a modular, Python-based simulation environment that enables the development and testing of multi-agent control algorithms. Zespol provides a flexible and extensible sandbox for initial research, with the potential for scaling to real-world applications. We provide a topological overview of the system and detailed descriptions of its plug-and-play elements. We demonstrate the fidelity of Zespol in simulated and real-word robotics by replicating existing works highlighting the simulation to real gap with the milling behavior. We plan to leverage Zespol's plug-and-play feature for neuromorphic computing in swarming scenarios, which involves using the modules in Zespol to simulate the behavior of neurons and their connections as synapses. This will enable optimizing and studying the emergent behavior of swarm systems in complex environments. Our goal is to gain a better understanding of the interplay between environmental factors and neural-like computations in swarming systems.

With the commercial application of automated vehicles (AVs), the sharing of roads between AVs and human-driven vehicles (HVs) becomes a common occurrence in the future. While research has focused on improving the safety and reliability of autonomous driving, it's also crucial to consider collaboration between AVs and HVs. Human-like interaction is a required capability for AVs, especially at common unsignalized intersections, as human drivers of HVs expect to maintain their driving habits for inter-vehicle interactions. This paper uses the social value orientation (SVO) in the decision-making of vehicles to describe the social interaction among multiple vehicles. Specifically, we define the quantitative calculation of the conflict-involved SVO at unsignalized intersections to enhance decision-making based on the reinforcement learning method. We use naturalistic driving scenarios with highly interactive motions for performance evaluation of the proposed method. Experimental results show that SVO is more effective in characterizing inter-vehicle interactions than conventional motion state parameters like velocity, and the proposed method can accurately reproduce naturalistic driving trajectories compared to behavior cloning.

Reinforcement learning (RL) has achieved remarkable success in complex robotic systems (eg. quadruped locomotion). In previous works, the RL-based controller was typically implemented as a single neural network with concatenated observation input. However, the corresponding learned policy is highly task-specific. Since all motors are controlled in a centralized way, out-of-distribution local observations can impact global motors through the single coupled neural network policy. In contrast, animals and humans can control their limbs separately. Inspired by this biological phenomenon, we propose a Decentralized motor skill (DEMOS) learning algorithm to automatically discover motor groups that can be decoupled from each other while preserving essential connections and then learn a decentralized motor control policy. Our method improves the robustness and generalization of the policy without sacrificing performance. Experiments on quadruped and humanoid robots demonstrate that the learned policy is robust against local motor malfunctions and can be transferred to new tasks.

We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations. This dataset is collected from a variety of biology experiments, and includes triplets of interacting mice (4.7 million frames video+pose tracking data, 10 million frames pose only), symbiotic beetle-ant interactions (10 million frames video data), and groups of interacting flies (4.4 million frames of pose tracking data). Accompanying these data, we introduce a panel of real-life downstream analysis tasks to assess the quality of learned representations by evaluating how well they preserve information about the experimental conditions (e.g. strain, time of day, optogenetic stimulation) and animal behavior. We test multiple state-of-the-art self-supervised video and trajectory representation learning methods to demonstrate the use of our benchmark, revealing that methods developed using human action datasets do not fully translate to animal datasets. We hope that our benchmark and dataset encourage a broader exploration of behavior representation learning methods across species and settings.

In this paper, we propose a second-order extension of the continuous-time game-theoretic mirror descent (MD) dynamics, referred to as MD2, which provably converges to mere (but not necessarily strict) variationally stable states (VSS) without using common auxiliary techniques such as time-averaging or discounting. We show that MD2 enjoys no-regret as well as an exponential rate of convergence towards strong VSS upon a slight modification. MD2 can also be used to derive many novel continuous-time primal-space dynamics. We then use stochastic approximation techniques to provide a convergence guarantee of discrete-time MD2 with noisy observations towards interior mere VSS. Selected simulations are provided to illustrate our results.

Social mediator robots facilitate human-human interactions by producing behavior strategies that positively influence how humans interact with each other in social settings. As robots for social mediation gain traction in the field of human-human-robot interaction, their ability to "understand" the humans in their environments becomes crucial. This objective requires models of human understanding that consider multiple humans in an interaction as a collective entity and represent the group dynamics that exist among its members. Group dynamics are defined as the influential actions, processes, and changes that occur within and between group interactants. Since an individual's behavior may be deeply influenced by their interactions with other group members, the social dynamics existing within a group can influence the behaviors, attitudes, and opinions of each individual and the group as a whole. Therefore, models of group dynamics are critical for a social mediator robot to be effective in its role. In this paper, we survey existing models of group dynamics and categorize them into models of social dominance, affect, social cohesion, conflict resolution, and engagement. We highlight the multimodal features these models utilize, and emphasize the importance of capturing the interpersonal aspects of a social interaction. Finally, we make a case for models of relational affect as an approach that may be able to capture a representation of human-human interactions that can be useful for social mediation.