In this demo work we develop a method to plan and coordinate a multi-agent team to gather information on demand. The data is periodically requested by a static Operation Center (OC) from changeable goals locations. The mission of the team is to reach these locations, taking measurements and delivering the data to the OC. Due to the limited communication range as well as signal attenuation because of the obstacles, the agents must travel to the OC, to upload the data. The agents can play two roles: ones as workers gathering data, the others as collectors traveling invariant paths for collecting the data of the workers to re-transmit it to the OC. The refreshing time of the delivered information depends on the number of available agents as well as of the scenario. The proposed algorithm finds out the best balance between the number of collectors-workers and the partition of the scenario into working areas in the planning phase, which provides the minimum refreshing time and will be the one executed by the agents.

Abstract: In the present work we address the problem of deploying a team of robots in a scenario where some locations of interest must be reached. Thus, a planning for a deployment is required, before sending the robots. The obstacles, the limited communication range, and the need of communicating to a base station, constrain the connectivity of the team and the deployment planning. We propose a method consisting of three algorithms: a distributed path planner to obtain communication-aware trajectories; a deployment planner providing dual-use of the robots, visiting primary goals and performing connectivity tasks; and a clustering algorithm to allocate the tasks to robots, and obtain the best goal visit order for the mission. Keywords: Multi-robot systems, deployment planning, communication-aware planning 1. INTRODUCTION characterize the signal in the environment, considering the variations suffered by the signal in the propagation media. The deployment of robot teams for exploration or environmental monitoring can be executed in many ways.

In the present paper we develop a distributed method to reconnect a multi-robot team after connectivity failures, caused by unpredictable environment changes, i.e. appearance of new obstacles. After the changes, the team is divided into different groups of robots. The groups have a limited communication range and only a partial information in their field of view about the current scenario. Their objective is to form a chain from a static base station to a goal location. In the proposed distributed replanning approach, the robots predict new plans for the other groups from the new observed information by each robot in the changed scenario, to restore the connectivity with a base station and reach the initial joint objective. If a solution exists, the method achieves the reconnection of all the groups in a unique chain. The proposed method is compared with other two cases: 1) when all the agents have full information of the environment, and 2) when some robots must move to reach other waiting robots for reconnection. Numerical simulations are provided to evaluate the proposed approach in the presence of unpredictable scenario changes.

In this paper we develop a method for planning and coordinating a multi-agent team deployment to periodically gather information on demand. A static operation center (OC) periodically requests information from changing goal locations. The objective is to gather data in the goals and to deliver it to the OC, balancing the refreshing time and the total number of information packages. The system automatically splits the team in two roles: workers to gather data, or collectors to retransmit the data to the OC. The proposed three step method: 1) finds out the best area partition for the workers; 2) obtains the best balance between workers and collectors, and with whom the workers must to communicate, a collector or the OC; 3) computes the best tour for the workers to visit the goals and deliver them to the OC or to a collector in movement. The method is tested in simulations in different scenarios, providing the best area partition algorithm and the best balance between collectors and workers.

Exploring the optimal management strategy for nitrogen and irrigation has a significant impact on crop yield, economic profit, and the environment. To tackle this optimization challenge, this paper introduces a deployable \textbf{CR}op Management system \textbf{O}ver all \textbf{P}ossible \textbf{S}tate availabilities (CROPS). CROPS employs a language model (LM) as a reinforcement learning (RL) agent to explore optimal management strategies within the Decision Support System for Agrotechnology Transfer (DSSAT) crop simulations. A distinguishing feature of this system is that the states used for decision-making are partially observed through random masking. Consequently, the RL agent is tasked with two primary objectives: optimizing management policies and inferring masked states. This approach significantly enhances the RL agent's robustness and adaptability across various real-world agricultural scenarios. Extensive experiments on maize crops in Florida, USA, and Zaragoza, Spain, validate the effectiveness of CROPS. Not only did CROPS achieve State-of-the-Art (SOTA) results across various evaluation metrics such as production, profit, and sustainability, but the trained management policies are also immediately deployable in over of ten millions of real-world contexts. Furthermore, the pre-trained policies possess a noise resilience property, which enables them to minimize potential sensor biases, ensuring robustness and generalizability. Finally, unlike previous methods, the strength of CROPS lies in its unified and elegant structure, which eliminates the need for pre-defined states or multi-stage training. These advancements highlight the potential of CROPS in revolutionizing agricultural practices.

Question answering is a natural language understanding task that involves reasoning over both explicit context and unstated, relevant domain knowledge. Large language models (LLMs), which underpin most contemporary question answering systems, struggle to induce how concepts relate in specialized domains such as medicine. Existing medical LLMs are also costly to train. In this work, we present MEG, a parameter-efficient approach for medical knowledge-augmented LLMs. MEG uses a lightweight mapping network to integrate graph embeddings into the LLM, enabling it to leverage external knowledge in a cost-effective way. We evaluate our method on four popular medical multiple-choice datasets and show that LLMs greatly benefit from the factual grounding provided by knowledge graph embeddings. MEG attains an average of +10.2% accuracy over the Mistral-Instruct baseline, and +6.7% over specialized models like BioMistral. We also show results based on Llama-3. Finally, we show that MEG's performance remains robust to the choice of graph encoder.

We present a method to increase the resolution of measurements of a physical system and subsequently predict its time evolution using thermodynamics-aware neural networks. Our method uses adversarial autoencoders, which reduce the dimensionality of the full order model to a set of latent variables that are enforced to match a prior, for example a normal distribution. Adversarial autoencoders are seen as generative models, and they can be trained to generate high-resolution samples from low-resoution inputs, meaning they can address the so-called super-resolution problem. Then, a second neural network is trained to learn the physical structure of the latent variables and predict their temporal evolution. This neural network is known as an structure-preserving neural network. It learns the metriplectic-structure of the system and applies a physical bias to ensure that the first and second principles of thermodynamics are fulfilled. The integrated trajectories are decoded to their original dimensionality, as well as to the higher dimensionality space produced by the adversarial autoencoder and they are compared to the ground truth solution. The method is tested with two examples of flow over a cylinder, where the fluid properties are varied between both examples.

It is possible to associate some concrete dimensions of these representations with concrete human-understandable features Prototypical Learning is based on the idea that there is a point so that a change of a feature produces changes in only a few (which we call prototype) around which the embeddings of a dimensions of the space. This is has some advantages such as class are clustered. It has shown promising results in scenarios (i) having more control over data creation in generative models with little labeled data or to design explainable models. Typically, [8], or (ii) providing the ability to explain and interpret prototypes are either defined as the average of the embeddings model predictions [9]. of a class or are designed to be trainable. In this work, In this paper we propose a modification on the prototypical we propose to predefine prototypes following human-specified systems that preserves their default advantages and, in addition, criteria, which simplify the training pipeline and brings different allows solving the two problems presented.

Monocular visual simultaneous localization and mapping (V-SLAM) is nowadays an irreplaceable tool in mobile robotics and augmented reality, where it performs robustly. However, human colonoscopies pose formidable challenges like occlusions, blur, light changes, lack of texture, deformation, water jets or tool interaction, which result in very frequent tracking losses. ORB-SLAM3, the top performing multiple-map V-SLAM, is unable to recover from them by merging sub-maps or relocalizing the camera, due to the poor performance of its place recognition algorithm based on ORB features and DBoW2 bag-of-words. We present CudaSIFT-SLAM, the first V-SLAM system able to process complete human colonoscopies in real-time. To overcome the limitations of ORB-SLAM3, we use SIFT instead of ORB features and replace the DBoW2 direct index with the more computationally demanding brute-force matching, being able to successfully match images separated in time for relocation and map merging. Real-time performance is achieved thanks to CudaSIFT, a GPU implementation for SIFT extraction and brute-force matching. We benchmark our system in the C3VD phantom colon dataset, and in a full real colonoscopy from the Endomapper dataset, demonstrating the capabilities to merge sub-maps and relocate in them, obtaining significantly longer sub-maps. Our system successfully maps in real-time 88 % of the frames in the C3VD dataset. In a real screening colonoscopy, despite the much higher prevalence of occluded and blurred frames, the mapping coverage is 53 % in carefully explored areas and 38 % in the full sequence, a 70 % improvement over ORB-SLAM3.

Computational simulation is a discipline that has been around for 80 years or so and that has emerged as a cornerstone tool across various scientific disciplines, facilitating the prediction of physical phenomena and enabling engineers to refine designs before costly experimental setups are pursued. Traditionally, these simulations have relied heavily on mathematical formulations, often expressed through partial differential equations (PDEs), to model complex systems in fields such as structural mechanics or fluid dynamics [1]. However, with the advent of the information era--the so-called fourth paradigm of science [2]--, a shift towards data-driven approaches, particularly deep learning algorithms, has garnered attention due to their ability to address the limitations of traditional methods, including handling nonlinear dynamics under real-time restrictions [3]. Deep learning algorithms, while powerful, are often computationally demanding and require extensive datasets, posing challenges in terms of scalability and generalization [4]. To address these challenges, recent research has explored novel architectures, such as geometric deep learning, which leverage problem structures to enhance performance and reduce data consumption [5-8]. This paradigm shift, which imposes specific constraints related to problem symmetries, has opened new avenues for learning from irregular and unstructured data representations, such as graphs [9]. At the same time, traditional mesh-based representations have long been favoured in modelling complex physical systems, offering adaptability and accuracy across various domains, from aerodynamics [10] to structural mechanics [11]. Despite their advantages, mesh representations have received relatively little attention in the realm of machine learning, where grid-based approaches dominate due to their compatibility with convolutional neural network (CNN) architectures [12]. Nonetheless, recent efforts have explored the potential of adaptive mesh representations in predicting the dynamics of physical systems, showcasing their ability to allocate computational resources optimally and adaptively change discretization during simulations [13].