Explore the vast range of titles available.

In multi-manipulator systems operating within shared workspaces, achieving collision-free posture control is challenging due to high degrees of freedom and complex inter-manipulator interactions. Traditional motion planning methods often struggle with scalability and computational efficiency in such settings, motivating the need for learning-based approaches. This paper presents a multi-agent deep reinforcement learning (MADRL) framework for real-time collision-free posture control of multiple manipulators. The proposed method employs a line-segment representation of manipulator links to enable efficient interlink distance computation to guide cooperative collision avoidance. Employing a centralized training and decentralized execution (CTDE) framework, the approach leverages global state information during training, while enabling each manipulator to rely on local observations for real-time collision-free trajectory planning. By integrating efficient state representation with a scalable training paradigm, the proposed framework provides a principled foundation for addressing coordination challenges in dense industrial workspaces. The approach is implemented and validated in NVIDIA Isaac Sim across various overlapping workspace scenarios. Compared to conventional state representations, the proposed method achieves faster learning convergence and superior computational efficiency. In pick-and-place tasks, collaborative multi-manipulator control reduces task completion time by over 50% compared to single-manipulator operation, while maintaining high success rates (>83%) under dense workspace conditions. These results confirm the effectiveness and scalability of the proposed framework for real-time, collision-free multi-manipulator control.

Gamecock chickens are one of the earliest recorded birds in China, and have accumulated some unique morphological and behavioral signatures such as large body size, muscularity and aggressive behavior, whereby being excellent breeding materials and a good model for studying bird muscular development and behavior. In this study, we sequenced 126 chicken genomes from 19 populations, including four commercial chicken breeds that are commonly farmed in China, 13 nationwide Chinese typical indigenous chicken breeds (including two Chinese gamecock breeds), one red jungle fowl from Guangxi Province of China and three gamecock chickens from Laos. Combined with 31 published chicken genomes from three populations, a comparative genomics analysis was performed across 157 chickens. We found a severe confounding effect on potential cold adaptation exerted by introgression from commercial chickens into Chinese indigenous chickens, and argued that the genetic introgression from commercial chickens into indigenous chickens should be seriously considered for identifying selection footprint in indigenous chickens. LX gamecock chickens might have played a core role in recent breeding and conservation of other Chinese gamecock chickens. Importantly, AGMO ( Alkylglycerol monooxygenase ) and CPZ ( Carboxypeptidase Z ) might be crucial for determining the behavioral pattern of gamecock chickens, while ISPD ( Isoprenoid synthase domain containing ) might be essential for the muscularity of gamecock chickens. Our results can further the understanding of the evolution of Chinese gamecock chickens, especially the genetic basis of gamecock chickens revealed here was valuable for us to better understand the mechanisms underlying the behavioral pattern and the muscular development in chicken.

Metabolites from intestinal microbes modulate the mucosal immune system by regulating the polarization and expansion of T cells. Whether the microbial metabolites influence macrophage polarization, however, is poorly understood. Here, we show that the large bowel microbial fermentation product, butyrate, facilitates M2 macrophage polarization, in vitro and in vivo . The supernatant from butyrate-treated M2 macrophage increased the migration and enhanced the wound closure rate of MLE-12 cells. Butyrate attenuated intestinal inflammation in mice with dextran sulfate sodium (DSS)-induced colitis, with a significant increase in colonic expression of the M2 macrophage-associated protein, Arg1. M2 macrophage treated with butyrate, had increased activation of the H3K9/STAT6 signaling pathway, suggesting a mechanism for butyrate facilitated M2 macrophage polarization. Collectively, our study indicated that commensal microbe-derived butyrate is a novel activator of STAT6-mediated transcription through H3K9 acetylation driving M2 macrophage polarization and delineated new insights into the immune interplay underlying inflammatory bowel disease.

Defect inspection is important to ensure consistent quality and efficiency in industrial manufacturing. Recently, machine vision systems integrating artificial intelligence (AI)-based inspection algorithms have exhibited promising performance in various applications, but practically, they often suffer from data imbalance. This paper proposes a defect inspection method using a one-class classification (OCC) model to deal with imbalanced datasets. A two-stream network architecture consisting of global and local feature extractor networks is presented, which can alleviate the representation collapse problem of OCC. By combining an object-oriented invariant feature vector with a training-data-oriented local feature vector, the proposed two-stream network model prevents the decision boundary from collapsing to the training dataset and obtains an appropriate decision boundary. The performance of the proposed model is demonstrated in the practical application of automotive-airbag bracket-welding defect inspection. The effects of the classification layer and two-stream network architecture on the overall inspection accuracy were clarified by using image samples collected in a controlled laboratory environment and from a production site. The results are compared with those of a previous classification model, demonstrating that the proposed model can improve the accuracy, precision, and F1 score by up to 8.19%, 10.74%, and 4.02%, respectively.

Taekwondo has evolved from a traditional martial art into an official Olympic sport. This study introduces a novel action recognition model tailored for Taekwondo unit actions, utilizing joint-motion data acquired via wearable inertial measurement unit (IMU) sensors. The utilization of IMU sensor-measured motion data facilitates the capture of the intricate and rapid movements characteristic of Taekwondo techniques. The model, underpinned by a conventional convolutional neural network (CNN)-based image classification framework, synthesizes action images to represent individual Taekwondo unit actions. These action images are generated by mapping joint-motion profiles onto the RGB color space, thus encapsulating the motion dynamics of a single unit action within a solitary image. To further refine the representation of rapid movements within these images, a time-warping technique was applied, adjusting motion profiles in relation to the velocity of the action. The effectiveness of the proposed model was assessed using a dataset compiled from 40 Taekwondo experts, yielding remarkable outcomes: an accuracy of 0.998, a precision of 0.983, a recall of 0.982, and an F1 score of 0.982. These results underscore this time-warping technique’s contribution to enhancing feature representation, as well as the proposed method’s scalability and effectiveness in recognizing Taekwondo unit actions.

Contemporary societies exhibit delayed reproductive age and increased life expectancy. While the male reproductive system demonstrates relatively delayed aging compared to that of females, increasing age substantially impacts its function. A characteristic manifestation is age-induced testosterone decline. Testosterone, a crucial male sex hormone, plays pivotal roles in spermatogenesis and sexual function, and contributes significantly to metabolism, psychology, and cardiovascular health. Aging exerts profound effects on the hypothalamic-pituitary–gonadal axis and Leydig cells, precipitating testosterone reduction, which adversely affects male health. Exogenous testosterone supplementation can partially ameliorate age-related testosterone deficiency; however, its long-term safety remains contentious. Preserving endogenous testosterone production capacity during the aging process warrants further investigation as a potential intervention strategy.

Newcastle disease (ND) is one of the most serious viral diseases affecting chickens and is caused by Newcastle disease virus (NDV), an avian paramyxovirus serotype-1. The virus contains five structural proteins and two nonstructural proteins that interact with the host proteins involved in viral infection and host antiviral responses. Currently, several NDV strains have been molecularly characterized; however, a comprehensive overview of NDV in chickens that addresses recent findings is lacking. This review summarizes the current report of the molecular structure of NDV, including candidate genes and genomic regions, virulence and route of infection, mechanisms of resistance, host immune response, disease resistance mechanisms and effects of NDV on chicken immune performance. Therefore, this review can be used by researchers seeking a comprehensive understanding that can be applied in future breeding programs aimed at enhancing disease resistance.

Issues of fairness and consistency in Taekwondo poomsae evaluation have often occurred due to the lack of an objective evaluation method. This study proposes a three-dimensional (3D) convolutional neural network–based action recognition model for an objective evaluation of Taekwondo poomsae. The model exhibits robust recognition performance regardless of variations in the viewpoints by reducing the discrepancy between the training and test images. It uses 3D skeletons of poomsae unit actions collected using a full-body motion-capture suit to generate synthesized two-dimensional (2D) skeletons from desired viewpoints. The 2D skeletons obtained from diverse viewpoints form the training dataset, on which the model is trained to ensure consistent recognition performance regardless of the viewpoint. The performance of the model was evaluated against various test datasets, including projected 2D skeletons and RGB images captured from diverse viewpoints. Comparison of the performance of the proposed model with those of previously reported action recognition models demonstrated the superiority of the proposed model, underscoring its effectiveness in recognizing and classifying Taekwondo poomsae actions.

Background Globally, the Newcastle disease virus (NDV) is a seriously important pathogen and results in substantial economic losses in the poultry industry. To mitigate this pathogen, the poultry industry has employed intensive breeding programs aimed at selecting genetic Lines that promote resistance and enhance immune response. Resistance to infection occurs at multiple levels and involves genotype-specific polymorphisms in the host. To date, the influence of genetic variations on the immune response within the same chicken Lines at the genotype-specific level is not fully understood. Therefore, it is important to understand the host genetic resistance that plays a role after NDV infection. This study aimed to investigate genotype-specific immune responses in chicken spleens following NDV infection at 7 days post-infection (7dpi), Samples were analyzed for differentially expressed genes (DEGs) using high-throughput RNA sequencing approaches. Results Twelve cDNA Libraries from LNH chicken spleens were compared with those of NDV-infected birds across the AA and GG genotypes. A total of 9886 genes were compared, of which 1348 were upregulated (833) and downregulated (515). Of these, 552 genes, with 415 upregulated and 137 downregulated genes, were differentially expressed (DE) between the two pairwise comparison groups: Control_AA vs. Immune_AA (AA group) and Control_GG vs. Immune_GG (GG group). Higher number of differentially expressed genes (407 DEGs), with 349 upregulated and 58 downregulated genes, were identified in chickens with the GG genotype, whereas 142 genes, with 63 upregulated and 79 downregulated genes, were observed in chickens with the AA genotype. In this study, a set of seven candidate genes (LECT1, MR1, MYH3, USH1C, NMU, BG8, and CCN3) was identified associated with the immune response in chickens. Further analysis revealed that DEGs in the spleen were enriched in various signaling pathways, such as neuroactive ligand-receptor interactions, tight junctions, and glycolysis/gluconeogenesis pathways, suggesting their potential role in immune resilience. Conclusions RNA-seq analysis revealed immune-related genes and pathways involved in the immune response in the chicken spleen. The results indicate that chickens with the GG genotype exhibited higher levels of differentially expressed genes (DEGs), potentially linked to NDV responses. Our findings also offer valuable transcriptomic insights for the comparative analysis of molecular mechanisms underlying immune response in LNH chickens and have practical implications for enhancing chicken breeding programs.

Complex traits exhibit a highly polygenic architecture that complicates gene mapping and molecular characterization. As a model organism for birds, chickens possess high-quality reference panels, functional annotations, and molecular quantitative trait locus maps. However, the genetic mechanisms underlying growth traits have not been systematically analyzed. Here, we develop a 16-generation advanced intercross line of chickens to enhance informative recombination and identify 154 single-gene quantitative trait loci. We use multiple co-localization methods to establish a network landscape of tissue-specific regulatory mutations and functional gene relationships. We leverage gene-clustering and restoration quantitative trait loci within the omnigenic model framework to elucidate the genetic regulation system of growth traits. Cross-species comparisons show the conserved functions of growth-related genes and divergent features of regulatory mechanisms in mammals and birds. Complex traits present challenges for gene mapping and molecular characterization. Here, the authors develop a 16-generation intercross line of chickens to explore the genetic architecture of complex traits in chicken.