The field of bio-inspired soft grippers has emerged as a transformative area of research with profound implications for biomedical applications. This book chapter provides a comprehensive overview of the principles, developments, challenges, and prospects of soft grippers that draw inspiration from biological systems. Bio-inspired soft grippers have gained prominence due to their unique characteristics, including compliance, adaptability, and biocompatibility. They have revolutionized the way we approach biomedical tasks, offering safer interactions with delicate tissues and enabling complex operations that were once inconceivable with rigid tools. The chapter delves into the fundamental importance of soft grippers in biomedical contexts. It outlines their significance in surgeries, diagnostics, tissue engineering, and various medical interventions. Soft grippers have the capacity to mimic the intricate movements of biological organisms, facilitating minimally invasive procedures and enhancing patient outcomes. A historical perspective traces the evolution of soft grippers in biomedical research, highlighting key milestones and breakthroughs. From early attempts to emulate the dexterity of octopus tentacles to the latest advancements in soft lithography and biomaterials, the journey has been marked by ingenuity and collaboration across multiple disciplines. Motivations for adopting soft grippers in biomedical applications are explored, emphasizing their ability to reduce invasiveness, increase precision, and provide adaptability to complex anatomical structures. The requirements and challenges in designing grippers fit for medical contexts are outlined, encompassing biocompatibility, sterilization, control, and integration.

Deep learning, particularly Convolutional Neural Networks (CNNs), has gained significant attention for its effectiveness in computer vision, especially in agricultural tasks. Recent advancements in instance segmentation have improved image classification accuracy. In this work, we introduce a comprehensive dataset for training neural networks to detect weeds and soy plants through instance segmentation. Our dataset covers various stages of soy growth, offering a chronological perspective on weed invasion's impact, with 1,000 meticulously annotated images. We also provide 6 state of the art models, trained in this dataset, that can understand and detect soy and weed in every stage of the plantation process. By using this dataset for weed and soy segmentation, we achieved a segmentation average precision of 79.1% and an average recall of 69.2% across all plant classes, with the YOLOv8X model. Moreover, the YOLOv8M model attained 78.7% mean average precision (mAp-50) in caruru weed segmentation, 69.7% in grassy weed segmentation, and 90.1% in soy plant segmentation.

Data scarcity in the brain-computer interface field can be alleviated through the use of generative models, specifically diffusion models. While diffusion models have previously been successfully applied to electroencephalogram (EEG) data, existing models lack flexibility w.r.t.~sampling or require alternative representations of the EEG data. To overcome these limitations, we introduce a novel approach to conditional diffusion models that utilizes classifier-free guidance to directly generate subject-, session-, and class-specific EEG data. In addition to commonly used metrics, domain-specific metrics are employed to evaluate the specificity of the generated samples. The results indicate that the proposed model can generate EEG data that resembles real data for each subject, session, and class.

Normalizing flows have shown great success as general-purpose density estimators. However, many real world applications require the use of domain-specific knowledge, which normalizing flows cannot readily incorporate. We propose embedded-model flows (EMF), which alternate general-purpose transformations with structured layers that embed domain-specific inductive biases. These layers are automatically constructed by converting user-specified differentiable probabilistic models into equivalent bijective transformations. We also introduce gated structured layers, which allow bypassing the parts of the models that fail to capture the statistics of the data. We demonstrate that EMFs can be used to induce desirable properties such as multimodality, hierarchical coupling and continuity. Furthermore, we show that EMFs enable a high performance form of variational inference where the structure of the prior model is embedded in the variational architecture. In our experiments, we show that this approach outperforms state-of-the-art methods in common structured inference problems.