J. M. Díaz-Báñez

M. A. Pérez-Cutiño, J. Valverde, J. Capitán et al.

In the context of Concentrated Solar Power (CSP) plants, aerial images captured by drones present a unique set of challenges. Unlike urban or natural landscapes commonly found in existing datasets, solar fields contain highly reflective surfaces, and domain-specific elements that are uncommon in traditional computer vision benchmarks. As a result, machine learning models trained on generic datasets struggle to generalize to this setting without extensive retraining and large volumes of annotated data. However, collecting and labeling such data is costly and time-consuming, making it impractical for rapid deployment in industrial applications. To address this issue, we propose a novel approach: the creation of AerialCSP, a virtual dataset that simulates aerial imagery of CSP plants. By generating synthetic data that closely mimic real-world conditions, our objective is to facilitate pretraining of models before deployment, significantly reducing the need for extensive manual labeling. Our main contributions are threefold: (1) we introduce AerialCSP, a high-quality synthetic dataset for aerial inspection of CSP plants, providing annotated data for object detection and image segmentation; (2) we benchmark multiple models on AerialCSP, establishing a baseline for CSP-related vision tasks; and (3) we demonstrate that pretraining on AerialCSP significantly improves real-world fault detection, particularly for rare and small defects, reducing the need for extensive manual labeling. AerialCSP is made publicly available at https://mpcutino.github.io/aerialcsp/.

J. M. Díaz-Báñez, L. E. Caraballo, M. A. Lopez et al.

This paper addresses a synchronization problem that arises when a team of aerial robots (ARs) need to communicate while performing assigned tasks in a cooperative scenario. Each robot has a limited communication range and flies within a previously assigned closed trajectory. When two robots are close enough, a communication link may be established, allowing the robots to exchange information. The goal is to schedule the flights such that the entire system can be synchronized for maximum information exchange, that is, every pair of neighbors always visit the feasible communication link at the same time. We propose an algorithm for scheduling a team of robots in this scenario and propose a robust framework in which the synchronization of a large team of robots is assured. The approach allows us to design a fault-tolerant system that can be used for multiple tasks such as surveillance, area exploration, searching for targets in a hazardous environment, and assembly and structure construction, to name a few.

S. Bereg, L. E. Caraballo, J. M. Díaz-Báñez et al.

Fault tolerance is increasingly important for unmanned autonomous vehicles. For example, in a multi robot system the agents need the ability to effectively detect and tolerate internal failures in order to continue performing their tasks without the need for immediate human intervention. The system must react to unplanned events in order to optimize the task allocation between the robots. In a broad sense, the resilience of a system can be defined as the ability to maintain or recover a stable state when subject to disturbance and it is related to the concept of robustness in industrial systems. In this paper, we study the resilience in a synchronized multi-robot system stated as follows:Consider a team of $n$ (ground or aerial) robots each moving along predetermined periodic closed trajectories. Each of the agents needs to communicate informationabout its operation to other agents, but the communication links have a limited range. Hence, when two agents are within communication range, a communication link is established, and information is exchanged. Thus, two neighbors are synchronized if they visit the communication link at the same time and a multi-robot system is called synchronized if each pair of neighbors is synchronized. If a set of robots left the system, then some trajectories has no robots. In these cases, when an alive robot detects no neighboring robot then it pass to this neighboring trajectory to assume the unattended task. In this framework, a fault-tolerance measure is introduced: the resilience of the system is the largest number of robots that can fail while executing the global task. Interesting combinatorial properties of the resilience are showed that allow to know its value for some usual scenarios.