Search

The federated learning (FL) paradigm aims to distribute the computational burden of the training process among several computation units, usually called agents or workers, while preserving private local training datasets. This is generally achieved by resorting to a server–worker architecture where agents iteratively update local models and communicate local parameters to a server that aggregates and returns them to the agents. However, the presence of adversarial agents, which may intentionally exchange malicious parameters or may have corrupted local datasets, can jeopardize the FL process. Therefore, we propose selective trimmed average (SETA), which is a resilient algorithm to cope with the undesirable effects of a number of misbehaving agents in the global model. SETA is based on properly filtering and combining the exchanged parameters. We mathematically prove that the proposed algorithm is resilient against data and local model poisoning attacks. Most resilient methods presented so far in the literature assume that a trusted server is in hand. In contrast, our algorithm works both in server–worker and shared memory architectures, where the latter excludes the necessity of a trusted server. The theoretical findings are corroborated through numerical results on MNIST dataset and on multiclass weather dataset (MWD).

The solid state of four novel S-(+)-Naproxen (S-Nap) diastereomeric salts with cis-1-amino-2-indanol (SR-AIand RS-AIenantiomers) is reported. The anhydrous SR-AI_S-Nap_Ais the only obtained phase in all the experimental conditions used, while the kinetically preferred diastereomeric salt RS-AI_S-Nap_A1forms only in certain conditions and undergoes an irreversible phase transition to RS-AI_S-Nap_A2after melting; this second phase was obtained even by dehydration of the monohydrate salt RS-AI_S-Nap_W. The preferred crystallization of SR-AI_S-Nap_Awas observed when S-Napwas introduced in a solution containing equimolar quantity of the racemic cis-1-amino-2-indanol, in spite of the strict similarity of the crystal packings of SR-AI_S-Nap_Aand RS-AI_S-Nap_A1. With the aim of trying to explain the preference of S-Napfor the SR-AIenantiomer, an in-depth analysis and comparison of the diastereomeric salt crystal structures were carried out.

Human neutrophil elastase (HNE) plays an essential role in host defense against bacteria but is also involved in several respiratory diseases. Recent reports suggest that compounds exhibiting a combination of HNE inhibitory activity with antiradical properties may be therapeutically beneficial for the treatment of respiratory diseases involving inflammation and oxidative stress. We report here the synthesis and biological evaluation of novel ebselen analogues exhibiting HNE inhibitory and antiradical activities. HNE inhibition was evaluated in an enzymatic system using human HNE, whereas antiradical activity was evaluated in a cell-based assay system using phorbol 12-myristate 13-acetate (PMA)-stimulated murine bone marrow leukocytes as the source of reactive oxygen species (ROS). HNE inhibition was due to the N–CO group targeting Ser195-OH at position 2 of the scaffold, while antiradical activity was due to the presence of the selenium atom. The most active compounds 4d, 4f, and 4jexhibited a good balance between anti-HNE (IC50= 0.9–1.4 μM) and antiradical activity (IC50= 0.05–0.7 μM). Additionally, the solid-state structure of 4dwas determined and compared to that of the similar compound N-propionyl-1,2-benzisoselenazol-3(2H)-one.

In this work, we propose a route planning strategy for heterogeneous mobile robots in Precision Agriculture (PA) settings. Given a set of agricultural tasks to be performed at specific locations, we formulate a multi-Steiner Traveling Salesman Problem (TSP) to define the optimal assignment of these tasks to the robots as well as the respective optimal paths to be followed. The optimality criterion aims to minimize the total time required to execute all the tasks, as well as the cumulative execution times of the robots. Costs for travelling from one location to another, for maneuvering and for executing the task as well as limited energy capacity of the robots are considered. In addition, we propose a sub-optimal formulation to mitigate the computational complexity by leveraging the fact that generally in PA settings only a few locations require agricultural tasks in a certain period of interest compared to all possible locations in the field. A formal analysis of the optimality gap between the optimal and the sub-optimal formulations is provided. The effectiveness of the approach is validated in a simulated orchard where three heterogeneous aerial vehicles perform inspection tasks. Note to Practitioners—This paper aims at providing an efficient solution to PA needs by deploying a team of robots able to perform agricultural tasks at given locations in large-scale orchards. In particular, a novel general optimization problem is proposed that, given a set of mobile and possibly heterogeneous robots and a set of agricultural tasks to carry out, defines the assignment of these tasks to the robots as well as the routes to follow, while minimizing the total and the cumulative execution times of the robots. Existing approaches for route optimization in PA generally involves complete coverage of the field by one or multiple robots and do not account for maneuvering costs with general layouts of the field. We consider costs for travelling from one location to another, for executing the task and for maneuvering without any restriction on the layout of the plants as well as we take into account the limited energy capacity of the robots. We also provide a sub-optimal formulation which reduces the computational burden by relaxing the optimization of the maneuvering costs at the locations where agricultural tasks are carried out and formally derive the optimality gap. The proposed approach is flexible and can be easily adapted to any PA setting involving multiple mobile robots that are required to accomplish given tasks in an area of interest. We validate its effectiveness in a realistic simulated setup composed of three heterogeneous aerial vehicles performing inspection tasks. In future research, we aim to design algorithms to solve the proposed optimization problems in an efficient manner as well as to validate the formulations on real-world robotic platforms.

In this article, we present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces, focusing on manipulation of deformable objects. We propose a latent space roadmap (LSR) for task planning, which is a graph-based structure globally capturing the system dynamics in a low-dimensional latent space. Our framework consists of the following three parts. First, a mapping module (MM) that maps observations is given in the form of images into a structured latent space extracting the respective states as well as generates observations from the latent states. Second, the LSR, which builds and connects clusters containing similar states in order to find the latent plans between start and goal states, extracted by MM. Third, the action proposal module that complements the latent plan found by the LSR with the corresponding actions. We present a thorough investigation of our framework on simulated box stacking and rope/box manipulation tasks, and a folding task executed on a real robot.

The solid state of a novel hydrate form of 3,3′-diaminophenyl sulfone (3APS_0.5H2Oo) as well as its temperature-induced phase transitions is reported. On increasing the temperature, first a partial dehydration occurs, leading to the partially hydrated 3APS_0.1H2Oo, which then transforms into the monoclinic anhydrous form, 3APS_Am. Finally, by recrystallization of the melt 3APS_Am, a second anhydrous orthorhombic phase is obtained (3APS_Ao). This last phase transforms in 3APS_Amat a temperature between 360 and 400 K. XRD, DSC, TGA, HSM, and in silicodata have been used to better understand the dehydration mechanism. With the same aim, hydration/dehydration tests have been carried out. Finally, the dehydration behavior of 3APS_0.5H2Ohas been discussed in comparison with that of the dapsone hydrated phase 4APS_0.33H2Om.

Identifying pests and treating them in a timely manner is a crucial aspect of the Precision Agriculture (PA) paradigm. Driven by the needs of the H2020 European Project Pantheon, focused on precision farming in hazelnut orchards, we propose a pest management system for gall-mites, which cause severe symptoms on generative and vegetative buds. We develop a data-driven monitoring system based on You Only Look Once (YOLO) framework enabling the early detection of the pest infestation with mean average precision of 86.7% on a holdout dataset. We perform a thorough analysis on its performance using several data augmentation methods as well as validate its real-time computation capability on a NVIDIA Jetson Xavier, which can be easily integrated into any robotic platform. Finally, we contextualize the role of the proposed detection framework in a comprehensive pest management system.

In this paper, a strategy to handle the human safety in a multi-robot scenario is devised. In the presented framework, it is foreseen that robots are in charge of performing any cooperative manipulation task which is parameterized by a proper task function. The devised architecture answers to the increasing demand of strict cooperation between humans and robots, since it equips a general multi-robot cell with the feature of making robots and human working together. The human safety is properly handled by defining a safety index which depends both on the relative position and velocity of the human operator and robots. Then, the multi-robot task trajectory is properly scaled in order to ensure that the human safety never falls below a given threshold which can be set in worst conditions according to a minimum allowed distance. Simulations results are presented in order to prove the effectiveness of the approach.