In this work, we compare emergent communication (EC) built upon multi-agent deep reinforcement learning (MADRL) and language-oriented semantic communication (LSC) empowered by a pre-trained large language model (LLM) using human language. In a multi-agent remote navigation task, with multimodal input data comprising location and channel maps, it is shown that EC incurs high training cost and struggles when using multimodal data, whereas LSC yields high inference computing cost due to the LLM's large size. To address their respective bottlenecks, we propose a novel framework of language-guided EC (LEC) by guiding the EC training using LSC via knowledge distillation (KD). Simulations corroborate that LEC achieves faster travel time while avoiding areas with poor channel conditions, as well as speeding up the MADRL training convergence by up to 61.8% compared to EC.

A fundamental challenge in multi-agent reinforcement learning (MARL) is to learn the joint policy in an extremely large search space, which grows exponentially with the number of agents. Moreover, fully decentralized policy factorization significantly restricts the search space, which may lead to sub-optimal policies. In contrast, the auto-regressive joint policy can represent a much richer class of joint policies by factorizing the joint policy into the product of a series of conditional individual policies. While such factorization introduces the action dependency among agents explicitly in sequential execution, it does not take full advantage of the dependency during learning. In particular, the subsequent agents do not give the preceding agents feedback about their decisions. In this paper, we propose a new framework Back-Propagation Through Agents (BPTA) that directly accounts for both agents' own policy updates and the learning of their dependent counterparts. This is achieved by propagating the feedback through action chains. With the proposed framework, our Bidirectional Proximal Policy Optimisation (BPPO) outperforms the state-of-the-art methods. Extensive experiments on matrix games, StarCraftII v2, Multi-agent MuJoCo, and Google Research Football demonstrate the effectiveness of the proposed method.

The remarkable progress in Large Language Models (LLMs) opens up new avenues for addressing planning and decision-making problems in Multi-Agent Systems (MAS). However, as the number of agents increases, the issues of hallucination in LLMs and coordination in MAS have become increasingly prominent. Additionally, the efficient utilization of tokens emerges as a critical consideration when employing LLMs to facilitate the interactions among a substantial number of agents. In this paper, we develop a modular framework called LLaMAC to mitigate these challenges. LLaMAC implements a value distribution encoding similar to that found in the human brain, utilizing internal and external feedback mechanisms to facilitate collaboration and iterative reasoning among its modules. Through evaluations involving system resource allocation and robot grid transportation, we demonstrate the considerable advantages afforded by our proposed approach.

The analysis of (social) networks and multi-agent systems is a central theme in Artificial Intelligence. Some line of research deals with finding groups of agents that could work together to achieve a certain goal. To this end, different notions of so-called clusters or communities have been introduced in the literature of graphs and networks. Among these, defensive alliance is a kind of quantitative group structure. However, all studies on the alliance so for have ignored one aspect that is central to the formation of alliances on a very intuitive level, assuming that the agents are preconditioned concerning their attitude towards other agents: they prefer to be in some group (alliance) together with the agents they like, so that they are happy to help each other towards their common aim, possibly then working against the agents outside of their group that they dislike. Signed networks were introduced in the psychology literature to model liking and disliking between agents, generalizing graphs in a natural way. Hence, we propose the novel notion of a defensive alliance in the context of signed networks. We then investigate several natural algorithmic questions related to this notion. These, and also combinatorial findings, connect our notion to that of correlation clustering, which is a well-established idea of finding groups of agents within a signed network. Also, we introduce a new structural parameter for signed graphs, signed neighborhood diversity snd, and exhibit a parameterized algorithm that finds a smallest defensive alliance in a signed graph.

In recent years, digital twins have been proposed and implemented in various fields with potential applications ranging from prototyping to maintenance. Going forward, they are to enable numerous efficient and sustainable technologies, among them autonomous cars. However, despite a large body of research in many fields, academics have yet to agree on what exactly a digital twin is -- and as a result, what its capabilities and limitations might be. To further our understanding, we explore the capabilities of digital twins concerning diagnosis in the field of transportation. We conduct a systematic mapping study including digital twins of vehicles and their components, as well as transportation infrastructure. We discovered that few papers on digital twins describe any diagnostic process. Furthermore, most existing approaches appear limited to system monitoring or fault detection. These findings suggest that we need more research for diagnostic reasoning utilizing digital twins.

Optimal management of cross-asset infrastructure is a complex problem that requires adept inspection and maintenance policies addressing stochastic degradation impacts. According to the 2021 ASCE infrastructure report card [1], the US infrastructure is in fair to poor condition, earning a cumulative grade of C-, with components nearing the end of their useful lives and at high risk of failure. Pavements and bridges are indicative examples of inadequate infrastructure. One in every five miles of pavements is in poor condition, and 7.5% of bridges are structurally deficient. Economic analyses indicate that the US Department of Transportation fell 50% short of the funds required to sustain the national transportation system [1], which is also reflected in the available resources at individual State transportation agencies. The Virginia Department of Transportation, for example, reported that 50% of the State's bridges have exceeded their useful lives, and the required funds to replace them are five times greater than the estimated available funds over the next fifty years [2]. Inspection and Maintenance (I&M) policies are therefore indispensable towards efficiently distributing available economic and environmental resources for transportation systems. Making optimal decisions in complex and uncertain environments presents a variety of difficulties, including heterogeneity of asset classes, a high number of components resulting in vast state and action spaces, unreliable observations, limited availability of resources, and several related risks. Optimal solutions that define inspection and maintenance policies should thus incorporate concepts such as (i) online and offline data learning, (ii) imperfect information support, (iii) stochastic action outcomes considerations, and (iv) optimization of long-term goals under multiple constraints (e.g., safety targets or resource constraints).

One of the main problems that local authorities of large cities have to face is the regulation of urban mobility. They need to provide the means to allow for the efficient movement of people and distribution of goods. However, the provisioning of transportation services needs to take into account general global objectives, like reducing emissions and having more healthy living environments, which may not always be aligned with individual interests. Urban mobility is usually provided through a transport infrastructure that includes all the elements that support mobility. On many occasions, the capacity of the elements of this infrastructure is lower than the actual demand and thus different transportation activities compete for their use. In this paper, we argue that scarce transport infrastructure elements should be assigned dynamically and in a prioritised manner to transport activities that have a higher utility from the point of view of society; for example, activities that produce less pollution and provide more value to society. In this paper, we define a general model for prioritizing the use of a particular type of transportation infrastructure element called time-unlimited elements, whose usage time is unknown a priori, and illustrate its dynamics through two use cases: vehicle-specific dynamic access restriction in city centres (i) based on the usage levels of available parking spaces and (ii) to assure sustained admissible air quality levels in the city centre. We carry out several experiments using the SUMO traffic simulation tool to evaluate our proposal.

In recent years many novel applications have appeared that promote the provision of services and activities in a collaborative manner. The key idea behind such systems is to take advantage of idle or underused capacities of existing resources, in order to provide improved services that assist people in their daily tasks, with additional functionality, enhanced efficiency, and/or reduced cost. Particularly in the domain of urban transportation, many researchers have put forward novel ideas, which are then implemented and evaluated through prototypes that usually draw upon AI methods and tools. However, such proposals also bring up multiple non-technical issues that need to be identified and addressed adequately if such systems are ever meant to be applied to the real world. While, in practice, legal and ethical aspects related to such AI-based systems are seldomly considered in the beginning of the research and development process, we argue that they not only restrict design decisions, but can also help guiding them. In this manuscript, we set out from a prototype of a taxi coordination service that mediates between individual (and autonomous) taxis and potential customers. After representing key aspects of its operation in a semi-structured manner, we analyse its viability from the viewpoint of current legal restrictions and constraints, so as to identify additional non-functional requirements as well as options to address them. Then, we go one step ahead, and actually modify the existing prototype to incorporate the previously identified recommendations. Performing experiments with this improved system helps us identify the most adequate option among several legally admissible alternatives.

Vehicle-sharing systems -- such as bike-, car-, or motorcycle-sharing systems -- have become increasingly popular in big cities in recent years. On the one hand, they provide a cheaper and environmentally friendlier means of transportation than private cars, and on the other hand, they satisfy the individual mobility demands of citizens better than traditional public transport systems. One of their advantages in this regard is their availability, e.g., the possibility of taking (or leaving) a vehicle almost anywhere in a city. This availability obviously depends on different strategic and operational management decisions and policies, such as the dimension of the fleet or the (re)distribution of vehicles. Agglutination problems -- where, due to usage patterns, available vehicles are concentrated in certain areas, whereas no vehicles are available in others -- are quite common in such systems, and need to be dealt with. Research has been dedicated to this problem, specifying different techniques to reduce imbalanced situations. In this paper, we present and compare strategies for recommending stations to users who wish to rent or return bikes in station-based bike-sharing systems. Our first contribution is a novel recommendation strategy based on queuing theory that recommends stations based on their utility to the user in terms of lower distance and higher probability of finding a bike or slot. Then, we go one step further, defining a strategy that recommends stations by combining the utility of a particular user with the utility of the global system, measured in terms of the improvement in the distribution of bikes and slots with respect to the expected future demand, with the aim of implicitly avoiding or alleviating balancing problems. We present several experiments to evaluate our proposal with real data from the bike sharing system BiciMAD in Madrid.

Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. While modeling pairwise relations has been widely studied in multi-agent interacting systems, the ability to capture larger-scale group-wise activities is limited. In this paper, we propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures, and we demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation. In addition to the edges between pairs of nodes (i.e., agents), we propose to infer hyperedges that adaptively connect multiple nodes to enable group-wise reasoning in an unsupervised manner. Our approach infers dynamically evolving relation graphs and hypergraphs to capture the evolution of relations, which the trajectory predictor employs to generate future states. Meanwhile, we propose to regularize the sharpness and sparsity of the learned relations and the smoothness of the relation evolution, which proves to enhance training stability and model performance. The proposed approach is validated on synthetic crowd simulations and real-world benchmark datasets. Experiments demonstrate that the approach infers reasonable relations and achieves state-of-the-art prediction performance. In addition, we present a deep reinforcement learning (DRL) framework for social robot navigation, which incorporates relational reasoning and trajectory prediction systematically. In a group-based crowd simulation, our method outperforms the strongest baseline by a significant margin in terms of safety, efficiency, and social compliance in dense, interactive scenarios.