Biomimetics最新文献

Moving in straight lines is a behaviour that enables organisms to search for food, move away from threats, and ultimately seek suitable environments in which to survive and reproduce. This study explores a vision-based technique for detecting a change in heading direction using the Milky Way (MW), one of the navigational cues that are known to be used by night-active insects. An algorithm is proposed that combines the YOLOv8m-seg model and normalised second central moments to calculate the MW orientation angle. This method addresses many likely scenarios where segmentation of the MW from the background by image thresholding or edge detection is not applicable, such as when the moon is substantial or when anthropogenic light is present. The proposed YOLOv8m-seg model achieves a segment mAP@0.5 of 84.7% on the validation dataset using our own training dataset of MW images. To explore its potential role in autonomous system applications, we compare night sky imagery and GPS heading data from a field trial in rural South Australia. The comparison results show that for short-term navigation, the segmented MW image can be used as a reliable orientation cue. There is a difference of roughly 5-10° between the proposed method and GT as the path involves left or right 90° turns at certain locations.

Simultaneous and cooperative muscle activation results in involuntary posture stabilization in vertebrates. However, the mechanism through which more muscles than joints contribute to this stabilization remains unclear. We developed a computational human body model with 949 muscle action lines and 22 joints and examined muscle activation patterns for stabilizing right upper or lower extremity motions at a neutral body posture (NBP) under gravity using actor-critic reinforcement learning (ACRL). Two feedback control models (FCM), muscle length change (FCM-ML) and joint angle differences, were applied to ACRL with a normalized Gaussian network (ACRL-NGN) or deep deterministic policy gradient. Our findings indicate that among the six control methods, ACRL-NGN with FCM-ML, utilizing solely antagonistic feedback control of muscle length change without relying on synergy pattern control or categorizing muscles as flexors, extensors, agonists, or synergists, achieved the most efficient involuntary NBP stabilization. This finding suggests that vertebrate muscles are fundamentally controlled without categorization of muscles for targeted joint motion and are involuntarily controlled to achieve the NBP, which is the most comfortable posture under gravity. Thus, ACRL-NGN with FCM-ML is suitable for controlling humanoid muscles and enables the development of a comfortable seat design.

Snakes can move freely on land, in lakes, and in other environments. During movement, the scales are in long-term contact with the external environment, providing protection to the body. In this study, we evaluated the mechanical properties and scratching performance of the ventral and dorsal scales from Dinodon rufozonatum, a generalist species that moves on both land and in streams under wet and dry conditions. The results showed that the elastic modulus and hardness of the dry scales were greater than those of the wet scales. The average scale friction coefficient under wet conditions (0.1588) was 9.3% greater than that under dry conditions (0.1453). The scales exhibit brittle damage in dry environments, while in wet environments, ductile damage is observed. This adaptation mechanism allows the scales to protect the body by dissipating energy and reducing stress concentration, ensuring efficient locomotion and durability in both terrestrial and aquatic environments. Understanding how this biomaterial adapts to environmental changes can inspire the development of bionic materials.

Stroke often causes neuromotor disabilities, impacting index finger function in daily activities. Due to the role of repetitive, even passive, finger movements in neuromuscular re-education and spasticity control, this study aims to design a rehabilitation exoskeleton based on the pulp pinch movement. The exoskeleton uses an underactuated RML topology with a single degree of mobility, customized from 3D scans of the patient's hand. It consists of eight links, incorporating two consecutive four-bar mechanisms and the third inversion of a crank-slider. A two-stage genetic optimization was applied, first to the location of the intermediate joint between the two four-bar mechanisms and later to the remaining dimensions. A targeted genetic optimization process monitored two quality metrics: average mechanical advantage from extension to flexion, and its variability. By analyzing the relationship between these metrics and key parameters at different synthesis stages, the population evaluated is reduced by up to 96.2%, compared to previous studies for the same problem. This custom-fit exoskeleton uses a small linear actuator to deliver a stable 12.45 N force to the fingertip with near-constant mechanical advantage during flexion. It enables repetitive pulp pinch movements in a flaccid finger, improving rehabilitation consistency and facilitating home-based therapy.

To facilitate the intelligent classification of unmanned highway toll stations, selecting effective and useful features is pivotal. This process involves achieving a tradeoff between the number of features and the classification accuracy while also reducing the acquisition costs of features. To address these challenges, a multimodal multi-objective feature selection (MMOFS) method is proposed in the current study. In the MMOFS, we utilize a multimodal multi-objective evolutionary algorithm to choose features for the unmanned highway toll station classification model and use the random forest method for classification. The primary contribution of the current study is to propose a feature selection method specifically designed for the classification model of unmanned highway toll stations. Experimental results using actual data from highway toll stations demonstrate that the proposed MMOFS outperforms the other two competitors in terms of PSP, HV, and IGD. Furthermore, the proposed algorithm can provide decision-makers with multiple equivalent feature selection schemes. This approach achieves a harmonious balance between the model complexity and the classification accuracy based on actual scenarios, thereby providing guidance for the construction of unmanned highway toll stations.

In light of recent global crises, including climate change, species extinction, the COVID-19 pandemic, social upheavals and energy supply challenges, this Special Issue of Biomimetics, entitled "Editorial Board Members' Collection Series: Biomimetic Design, Constructions and Devices in Times of Change", aims to explore innovative solutions through biomimetics. This collection features research on various biomimetic applications, such as the peptide-based detection of SARS-CoV-2 antibodies, ergonomic improvements for prolonged sitting, biomimicry industry trends, prosthetic foot functionality and agricultural machinery efficiency. The methods employed include peptide synthesis for diagnostics, simulation software for ergonomic designs, patent analysis for biomimicry trends and engineering discrete element methods for agricultural applications. The findings highlight significant advancements in health diagnostics, ergonomic safety, technological development, prosthetics and sustainable agriculture. The research underscores the potential of biomimetic approaches to address contemporary challenges by leveraging nature-inspired designs and processes. These insights contribute to a broader understanding of how biomimetic principles can lead to adaptive and sustainable solutions in times of change, promoting resilience and innovation across various fields.

In recent years, deep learning-based approaches, particularly those leveraging the Transformer architecture, have garnered widespread attention for network traffic anomaly detection. However, when dealing with noisy data sets, directly inputting network traffic sequences into Transformer networks often significantly degrades detection performance due to interference and noise across dimensions. In this paper, we propose a novel multi-channel network traffic anomaly detection model, MTC-Net, which reduces computational complexity and enhances the model's ability to capture long-distance dependencies. This is achieved by decomposing network traffic sequences into multiple unidimensional time sequences and introducing a patch-based strategy that enables each sub-sequence to retain local semantic information. A backbone network combining Transformer and CNN is employed to capture complex patterns, with information from all channels being fused at the final classification header in order to achieve modelling and detection of complex network traffic patterns. The experimental results demonstrate that MTC-Net outperforms existing state-of-the-art methods in several evaluation metrics, including accuracy, precision, recall, and F1 score, on four publicly available data sets: KDD Cup 99, NSL-KDD, UNSW-NB15, and CIC-IDS2017.

The Agile Robotics for Industrial Automation Competition (ARIAC) was established to advance flexible manufacturing, aiming to increase the agility of robotic assembly systems in unstructured and dynamic industrial environments. ARIAC 2023 introduced eight agility challenges involving faulty parts, flipped parts, faulty grippers, robot malfunctions, sensor blackouts, high-priority orders, insufficient parts, and human safety. Given the unpredictability of these scenarios, it is impractical to develop a specific strategy for each possible situation. To address these issues, this paper presents a hierarchical framework for autonomous robotic task generation and execution in dynamic scenarios. The framework is divided into a task level and an execution level. Initially, an immediate task management strategy is adopted at the task level, which reasonably decomposes dynamic tasks and allocates short-term tasks to the floor robot and ceiling robot. Later, at the execution level, each robot is designed with an agent architecture that combines PDDL planning with the quick response of behavior trees. Finally, the effectiveness and practicality of the proposed framework were thoroughly validated in ARIAC 2023.

Breast cancer remains a global health problem requiring effective diagnostic methods for early detection, in order to achieve the World Health Organization's ultimate goal of breast self-examination. A literature review indicates the urgency of improving diagnostic methods and identifies thermography as a promising, cost-effective, non-invasive, adjunctive, and complementary detection method. This research explores the potential of using machine learning techniques, specifically Bayesian networks combined with convolutional neural networks, to improve possible breast cancer diagnosis at early stages. Explainable artificial intelligence aims to clarify the reasoning behind any output of artificial neural network-based models. The proposed integration adds interpretability of the diagnosis, which is particularly significant for a medical diagnosis. We constructed two diagnostic expert models: Model A and Model B. In this research, Model A, combining thermal images after the explainable artificial intelligence process together with medical records, achieved an accuracy of 84.07%, while model B, which also includes a convolutional neural network prediction, achieved an accuracy of 90.93%. These results demonstrate the potential of explainable artificial intelligence to improve possible breast cancer diagnosis, with very high accuracy.

The wheel hub is an important component of the wheel, and a good hub design can significantly improve vehicle handling, stability, and braking performance, ensuring safe driving. This article optimized the hub structure through morphological aspects, where reducing the hub weight contributed to enhanced fuel efficiency and overall vehicle performance. By referencing honeycombed structures, a bionic hub design is numerically simulated using finite element analysis and response surface optimization. The results showed that under the optimization of the response surface analytical model, the maximum stress of the optimized bionic hub was 109.34 MPa, compared to 119.77 MPa for the standard hub, representing an 8.7% reduction in maximum stress. The standard hub weighs 34.02 kg, while the optimized hub weight was reduced to 29.89 kg, a decrease of 12.13%. A fatigue analysis on the optimized hub indicated that at a stress of 109.34 MPa, the minimum load cycles were 4.217 × 10⁵ at the connection point with the half-shaft, meeting the fatigue life requirements for commercial vehicle hubs outlined in the national standard GB/T 5334-2021.