As space becomes increasingly crowded and contested, robust autonomous capabilities for multi-agent environments are gaining critical importance. Current autonomous systems in space primarily rely on optimization-based path planning or long-range orbital maneuvers, which have not yet proven effective in adversarial scenarios where one satellite is actively pursuing another. We introduce Divergent Adversarial Reinforcement Learning (DARL), a two-stage Multi-Agent Reinforcement Learning (MARL) approach designed to train autonomous evasion strategies for satellites engaged with multiple adversarial spacecraft. Our method enhances exploration during training by promoting diverse adversarial strategies, leading to more robust and adaptable evader models. We validate DARL through a cat-and-mouse satellite scenario, modeled as a partially observable multi-agent capture the flag game where two adversarial `cat' spacecraft pursue a single `mouse' evader. DARL's performance is compared against several benchmarks, including an optimization-based satellite path planner, demonstrating its ability to produce highly robust models for adversarial multi-agent space environments.

Modern vehicles are equipped with multiple information-collection devices such as sensors and cameras, continuously generating a large volume of raw data. Accurately predicting the trajectories of neighboring vehicles is a vital component in understanding the complex driving environment. Yet, training trajectory prediction models is challenging in two ways. Processing the large-scale data is computation-intensive. Moreover, easy-medium driving scenarios often overwhelmingly dominate the dataset, leaving challenging driving scenarios such as dense traffic under-represented. For example, in the Argoverse motion prediction dataset, there are very few instances with $\ge 50$ agents, while scenarios with $10 \thicksim 20$ agents are far more common. In this paper, to mitigate data redundancy in the over-represented driving scenarios and to reduce the bias rooted in the data scarcity of complex ones, we propose a novel data-efficient training method based on coreset selection. This method strategically selects a small but representative subset of data while balancing the proportions of different scenario difficulties. To the best of our knowledge, we are the first to introduce a method capable of effectively condensing large-scale trajectory dataset, while achieving a state-of-the-art compression ratio. Notably, even when using only 50% of the Argoverse dataset, the model can be trained with little to no decline in performance. Moreover, the selected coreset maintains excellent generalization ability.

Humans possess innate collaborative capacities. However, effective teamwork often remains challenging. This study delves into the feasibility of collaboration within teams of rational, self-interested agents who engage in teamwork without the obligation to contribute. Drawing from psychological and game theoretical frameworks, we formalise teamwork as a one-shot aggregative game, integrating insights from Steiner's theory of group productivity. We characterise this novel game's Nash equilibria and propose a multiagent multi-armed bandit system that learns to converge to approximations of such equilibria. Our research contributes value to the areas of game theory and multiagent systems, paving the way for a better understanding of voluntary collaborative dynamics. We examine how team heterogeneity, task typology, and assessment difficulty influence agents' strategies and resulting teamwork outcomes. Finally, we empirically study the behaviour of work teams under incentive systems that defy analytical treatment. Our agents demonstrate human-like behaviour patterns, corroborating findings from social psychology research.

We investigate the problem of agent-to-agent interaction in decentralized (federated) learning over time-varying directed graphs, and, in doing so, propose a consensus-based algorithm called DSGTm-TV. The proposed algorithm incorporates gradient tracking and heavy-ball momentum to distributively optimize a global objective function, while preserving local data privacy. Under DSGTm-TV, agents will update local model parameters and gradient estimates using information exchange with neighboring agents enabled through row- and column-stochastic mixing matrices, which we show guarantee both consensus and optimality. Our analysis establishes that DSGTm-TV exhibits linear convergence to the exact global optimum when exact gradient information is available, and converges in expectation to a neighborhood of the global optimum when employing stochastic gradients. Moreover, in contrast to existing methods, DSGTm-TV preserves convergence for networks with uncoordinated stepsizes and momentum parameters, for which we provide explicit bounds. These results enable agents to operate in a fully decentralized manner, independently optimizing their local hyper-parameters. We demonstrate the efficacy of our approach via comparisons with state-of-the-art baselines on real-world image classification and natural language processing tasks.

Coordinating the motion of multiple robots in cluttered environments remains a computationally challenging task. We study the problem of minimizing the execution time of a set of geometric paths by a team of robots with state-dependent actuation constraints. We propose a Time-Optimal Path Parameterization (TOPP) algorithm for multiple car-like agents, where the modulation of the timing of every robot along its assigned path is employed to ensure collision avoidance and dynamic feasibility. This is achieved through the use of a priority queue to determine the order of trajectory execution for each robot while taking into account all possible collisions with higher priority robots in a spatiotemporal graph. We show a 10-20% reduction in makespan against existing state-of-the-art methods and validate our approach through simulations and hardware experiments.

Mediation is often treated as an extension of negotiation, without taking into account the unique role that norms and facts play in legal mediation. Additionally, current approaches for updating argument acceptability in response to changing variables frequently require the introduction of new arguments or the removal of existing ones, which can be inefficient and cumbersome in decision-making processes within legal disputes. In this paper, our contribution is two-fold. First, we introduce a QuAM (Quantitative Argumentation Mediate) framework, which integrates the parties' knowledge and the mediator's knowledge, including facts and legal norms, when determining the acceptability of a mediation goal. Second, we develop a new formalism to model the relationship between the acceptability of a goal argument and the values assigned to a variable associated with the argument. We use a real-world legal mediation as a running example to illustrate our approach.

The exchange of information is key in applications that involve multiple agents, such as search and rescue, military operations, and disaster response. In this work, we propose a simple and effective trajectory planning framework that tackles the design, deployment, and reconfiguration of a communication backbone by reframing the problem of networked multi-agent motion planning as a manipulator motion planning problem. Our approach works for backbones of variable configurations both in terms of the number of robots utilized and the distance limit between each robot. While research has been conducted on connection-restricted navigation for multi-robot systems in the last years, the field of manipulators is arguably more developed both in theory and practice. Hence, our methodology facilitates practical applications built on top of widely available motion planning algorithms and frameworks for manipulators.

For efficient and safe autonomous driving, it is essential that autonomous vehicles can predict the motion of other traffic agents. While highly accurate, current motion prediction models often impose significant challenges in terms of training resource requirements and deployment on embedded hardware. We propose a new efficient motion prediction model, which achieves highly competitive benchmark results while training only a few hours on a single GPU. Due to our lightweight architectural choices and the focus on reducing the required training resources, our model can easily be applied to custom datasets. Furthermore, its low inference latency makes it particularly suitable for deployment in autonomous applications with limited computing resources.

Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence. Multi-agent reinforcement learning (MARL) has demonstrated potential in modeling cooperative behaviors, but most RL-based approaches remain constrained to simplified simulations with limited dynamics or fixed scenarios. Previous attempts to deploy RL policy to real-world pursuit-evasion are largely restricted to two-dimensional scenarios, such as ground vehicles or UAVs at fixed altitudes. In this paper, we address multi-UAV pursuit-evasion by considering UAV dynamics and physical constraints. We introduce an evader prediction-enhanced network to tackle partial observability in cooperative strategy learning. Additionally, we propose an adaptive environment generator within MARL training, enabling higher exploration efficiency and better policy generalization across diverse scenarios. Simulations show our method significantly outperforms all baselines in challenging scenarios, generalizing to unseen scenarios with a 100% capture rate. Finally, we derive a feasible policy via a two-stage reward refinement and deploy the policy on real quadrotors in a zero-shot manner. To our knowledge, this is the first work to derive and deploy an RL-based policy using collective thrust and body rates control commands for multi-UAV pursuit-evasion in unknown environments. The open-source code and videos are available at https://sites.google.com/view/pursuit-evasion-rl.

In the field of locomotion task of quadruped robots, Blind Policy and Perceptive Policy each have their own advantages and limitations. The Blind Policy relies on preset sensor information and algorithms, suitable for known and structured environments, but it lacks adaptability in complex or unknown environments. The Perceptive Policy uses visual sensors to obtain detailed environmental information, allowing it to adapt to complex terrains, but its effectiveness is limited under occluded conditions, especially when perception fails. Unlike the Blind Policy, the Perceptive Policy is not as robust under these conditions. To address these challenges, we propose a MBC:Multi-Brain collaborative system that incorporates the concepts of Multi-Agent Reinforcement Learning and introduces collaboration between the Blind Policy and the Perceptive Policy. By applying this multi-policy collaborative model to a quadruped robot, the robot can maintain stable locomotion even when the perceptual system is impaired or observational data is incomplete. Our simulations and real-world experiments demonstrate that this system significantly improves the robot's passability and robustness against perception failures in complex environments, validating the effectiveness of multi-policy collaboration in enhancing robotic motion performance.