搜索结果：neurorobotics

In the high-stakes arena of aerial combat-a domain defined by extreme dynamics and unforgiving physical constraints-UAV swarms are currently squeezed between two extremes: the "tactical short-sightedness" of Multi-Agent Reinforcement Learning (MARL) and the "inference lag" of Large Language Models (LLMs). While MARL struggles to internalize the complex maneuverability priors required for expert flight, LLMs are simply too heavy to meet millisecond-level control demands. We bridge this gap by introducing a cognitive synergetic hierarchical framework that decouples strategic reasoning from tactical execution. Our architecture splits the workload between a "Strategic Brain" and a "Tactical Torso." For the Brain, we utilize a synergy between DeepSeek-R1 (70B) and its 7B distilled counterpart to create a collaborative inference engine. By capitalizing on the inherent sparsity of tactical logic in air combat, we implemented a speculative decoding mechanism that achieves an effective boost in decision throughput while maintaining the deep logic of the full 70B model. For the Torso, we developed an enhanced MAPPO algorithm that processes relative pose graphs via graph attention. By integrating a KL-divergence constraint into the loss function, we essentially force agents with different payloads-like scouts and attackers-to evolve specialized tactical personalities within a shared latent space. Experimental results using the JSBSim high-fidelity 6-DOF engine demonstrate that the swarm does more than just improve its exchange ratio. Further t-SNE manifold analysis and Chain-of-Thought visualizations confirm that our architecture successfully aligns symbolic intent with raw physical control. Most notably, through our "decision-reflection-evolution" loop, the system proved it could diagnose its own failures, and iteratively refine its own tactical instructions.

Joint actions among humans rely on the integration of multiple sensory modalities, most notably auditory and visual cues, which support explicit communication between partners. However, haptic feedback provides a direct, implicit channel for sensorimotor communication, and its contribution to fine motor coordination in joint actions remains largely unexplored. Here, we demonstrate that haptic communication, rendered through bidirectionally coupled wearable robots, outperforms traditional auditory-visual feedback in a complex and challenging real-life joint action: ensemble violin performance. First, we developed a pair of two-degree-of-freedom upper-limb exoskeletons capable of transparently following violinists' natural movements and rendering viscoelastic torques proportional to the joint angular deviation between the partners. Then, we designed a within-subject experiment with 20 violin duos performing a musical piece under four sensory feedback conditions: auditory (A), auditory-visual (AV), auditory-haptic (AH), and auditory-visual-haptic (AVH), across two tempi (72 and 100 beats per minute). Despite the musicians being unfamiliar with the robot-mediated haptic feedback and unaware of the bidirectional connection between them, haptic feedback (AH and AVH) substantially enhanced spatiotemporal coordination and dynamic musical alignment compared with the extensively trained auditory-visual feedback (A and AV). The multisensory feedback condition AVH yielded the highest scores across all measures. Our findings demonstrate that haptic feedback can support fine motor coordination in violin duo performance more effectively than visual cues, particularly for professional musicians, because of its implicit and embodied nature, and that it can be effectively delivered via wearable robots, expanding the paradigms of human-human sensorimotor interactions.

Deep learning technology promotes the development of single-image dehazing. However, many existing methods fail to fully consider the haze density and its spatial distribution, which limits the improvement of dehazing performance. To address this issue, we propose an attention-based multi-scale feature aggregation network (AMSA-Net) for single-image dehazing. AMSA-Net is an encoding and decoding structure. Its encoder and decoder are composed of multi-scale hybrid attention feature aggregation module (MSHA-FAM). The module can perceive the haze density and spatial information in the haze image, which helps to improve the dehazing effect. MSHA-FAM is composed of two key components: the scale-aware coordinate residual module (SCRM) and multi-scale feature refinement residual module (MSFRRM). SCRM uses improved coordinate attention to effectively capture haze density and spatial characteristics, thus significantly improving dehazing effect. MSFRRM extracts semantic features through up-sampling and down-sampling, and uses improved pixel attention mechanism to enhance key features. In the overall MSHA-FAM pipeline, SCRM first learns the density and spatial distribution characteristics of haze, then refines it through MSFRRM, so as to remove haze more effectively. The experimental results demonstrate that our proposed AMSA-Net is superior to the comparison methods in terms of dehazing quality. Ablation studies further verify the effectiveness of the proposed modules. In this work, we present AMSA-Net, which has achieved good dehazing performance and can provide high-quality input for subsequent computer vision tasks.

The biological sensorimotor system is a source of inspiration for the design of neuromorphic ballistic control systems. A large portion of sensorimotor-inspired research focuses on the sensory encoding and information processing stages of the system. However, research on broader task-performance systems, involving actuator control on the output side remains scarce. In this work, we develop and train a neuromuscular-inspired model to perform ballistic control. In the model, a spiking neural network's output spikes are used to generate twitch-like signals. These twitches are the basis for generating a continuous fluctuating output signal that is used to operate an actuator. We refer to the the used model as the Twitch Neural Network (TwNN). As a test case, the model is trained to control the paddle of an adapted version of the game of Pong. An adapted version of the Direct Feedback Alignment learning rule, specifically for integrate-and-fire neurons, is introduced. The new rule avoids the update-locking problem of backpropagation, allowing network weight updates in parallel. The model output consists of one group of agonist-innervating motor neurons, and one group of antagonist-innervating motor neurons. We find that it is possible to teach a neuromuscular-inspired system to control the paddle in the game of Pong with the adapted Direct Feedback Alignment learning rule. The best-performing baseline model achieved a hit rate of 96%. By applying logarithmic scaling to the output activity, a hit rate of 98% could be achieved. Finally, by replacing the neuromorphically unrealistic exact summation steps with leaky integrators in training, the range of good learning parameters became more narrow and clear. The best-performing model reaches a hit rate of 99%. Threshold analysis during training has shown that learning is robust to a variety of neuron thresholds. Noise analysis has shown that the system is robust to membrane potential noise during inference for uniform noise up to values in the order of around 0.1-1% of the neuron threshold value per time step.

Inhibitory interneuron diversity is a central feature of cortical circuits. The IN-CODE consortium seeks to combine large-scale recordings of interneuron types with machine-learning tools to identify the role of their physiological features, connectivity motifs, and cooperativity in cognitive functions.

Direct cellular reprogramming, the conversion of one somatic cell type into another, represents a remarkable advancement in regenerative medicine. Its potential to transform fibrotic tissue into functional parenchyma underscores its therapeutic promise. However, several critical challenges remain unresolved, including limited reprogramming efficiency, the long-term functional stability of converted cells, their integration within pre-existing cellular circuits, and safety concerns related to transgene integration and immunological responses to reprogramming-based viral vectors. Approaches based on the exogenous administration of recombinant proteins and miRNAs have also emerged, though these rely on factors that are naturally prone to exhaustion and degradation, potentially restricting their efficacy. This review is divided into three main sections. The first part addresses direct cellular reprogramming in the context of other cell-based applications, outlining its main applications and current biological limitations. The second part examines how different biomaterials, ranging from hydrogel scaffolds to nanoparticles, can modulate direct cellular reprogramming by providing mechanical and topographical cues and by enabling tighter control over the concentration and spatiotemporal dynamics of reprogramming factors and viral vectors. The third part discusses key findings in biomaterial-assisted reprogramming strategies, highlighting emerging opportunities for clinically translatable approaches. The convergence of regenerative biology and biomaterials science may ultimately generate advanced gel-based and hybrid cellular reprogramming platforms for in vitro testing and, in situ applications, for promoting cell fate stabilization and facilitating the regeneration of damaged tissues and organs.

[This corrects the article DOI: 10.3389/fnbot.2026.1768219.].

Adaptive lower-limb neurorobotics requires gaitd-state representations that preserve locomotor structure without reducing post-stroke walking to a single asymmetry score or opaque latent embedding. Because post-stroke gait is multimodal and side dependent, transparent side-aware representations may better support future adaptive-assistance design than modality-isolated summaries. This secondary analysis used a public multimodal gait dataset comprising 138 able-bodied adults and 50 adults with stroke. The analytic space was restricted to 11 waveform domains shared across public exports: four sagittal kinematic waveforms and seven repository-normalized surface electromyography waveforms, each represented by 1,001 time-normalized points. Stroke waveforms were organized into paretic, non-paretic, bilateral-mean, and side-difference views, with side difference defined as paretic minus non-paretic. Domain-view functional principal component analysis retained 90% cumulative variance, capped at three components per block; family-level reduction retained 90% variance, capped at eight components. Candidate Ward hierarchical and K-means solutions from two to five states were screened in kinematics-only, sEMG-only, fused, paretic-only, and erector-spinae-excluded spaces. The retained fused side-aware solution organized the strict complete-case stroke cohort (n = 43) into three states: State 1 (n = 12), State 2 (n = 18), and State 3 (n = 13). The strongest fused two-state K-means comparator showed higher compactness and resampling stability than the retained three-state solution [silhouette 0.189; bootstrap adjusted Rand index (ARI) 0.876 versus silhouette 0.155; bootstrap ARI 0.633]. However, the three-state solution was retained as a representation-level choice because it avoided trivial micro-clusters, preserved explicit multimodal side-aware structure, and enabled clearer waveform-level interpretation. Sensitivity analyses showed identical assignments after erector-spinae exclusion (ARI = 1.000), partial concordance under robust scaling (ARI = 0.785), and material reassignment when the block cap was reduced to two components (ARI = 0.335). The strongest domain contributors were ankle angle (1.000), vastus lateralis sEMG (0.898), knee angle (0.866), gastrocnemius sEMG (0.851), and tibialis anterior sEMG (0.840). Public waveform exports supported an internally interpretable, side-aware multimodal representation of post-stroke gait relevant to neurorobotic state-representation design. This contribution remains exploratory and representational, not clinical, interventional, real-time, or controller-validating; for future studies, it should be interpreted as a hypothesis-generating framework.

Resource-constrained environmental perception requires autonomous robots and embodied intelligent systems to process visual signals efficiently while preserving image fidelity in complex real-world environments. However, converting high dynamic range RAW sensor data into perceptually faithful RGB images remains computationally expensive, thereby limiting the deployment of neural image signal processors on edge platforms with restricted memory, energy, and computational budgets. Consequently, this study proposes the enhanced quantized image signal processor (EQISP), comprising the quantized convolutional neural network (QCNN) and the unified pyramid fusion algorithm (UPFA). QCNN employs dynamic fixed-point hybrid quantization, which adjusts parameter ranges according to the linear relationship between threshold standard deviation and fractional length, thereby significantly reducing the computational load. Meanwhile, UPFA utilizes Gaussian pyramids to capture global illumination and Laplacian pyramids to preserve fine details, enabling multi-scale, multi-exposure fusion and iterative reconstruction to mitigate detail loss induced by quantization. Comprehensive comparative experiments demonstrated that EQISP achieved a PSNR of 22.90 dB, an SSIM of 0.9278, and 164.843 GFLOPs. Compared with the PyNET baseline, EQISP improved the PSNR by 1.71 dB while reducing the computational cost by a factor of 4.24. Furthermore, deployment experiments on an NVIDIA Jetson TX2 development board showed that EQISP achieved a model size of 57 MB, an inference latency of 189 ms, an inference speed of 6.1 FPS, and a peak memory usage of 2.2 GB. These results provide practical evidence that EQISP can serve as an efficient and scalable visual front end for resource-constrained embodied perception systems.

Sophisticated hand movements are essential for daily activities, but central neurological impairments often compromise them. Since full recovery through conventional physiotherapy is rare, assistance is crucial. While neural implants show promise, clinical use remains distant, urging immediate assistive alternatives. Current exoskeletons and neurostimulation garments lack sufficient motor support and sensory feedback, limiting dexterity. We developed a neurorobotic system combining portable exoskeletons with targeted neurostimulation via custom-made e-sleeve and tested it in 14 individuals with central neural injuries. We provide evidence of restored finger mobility and tactile perception, even in patients with clinically complete sensory loss, by recruiting residual peripheral pathways. Eight participants completed functional assessments, in which they exploited neurostimulation to improve grasp precision and enhance strength. This enabled manipulation of fragile and cumbersome objects, essential for everyday activities. Personalized assistive technologies have clinical potential to promote independence and support the reintegration of people with neurological impairments into society.

The rapid advancement of unmanned aerial vehicles (UAVs) in disaster response and environmental monitoring has underscored the growing importance of real-time object detection within UAV swarm networks. However, the non-independent and identically distributed (non-IID) characteristics of data in UAV networks present significant challenges to model convergence and adaptability. To tackle these challenges, this study introduces a robust federated UAV object detection framework tailored for non-IID data distributions. The framework aims to enhance adaptability across clients, thereby improving both detection performance and convergence speed. Our approach includes a self-distillation mechanism that leverages personalized knowledge from local model historical states to guide current local training, striking a balance between specialization and adaptability. Additionally, we propose a drift compensation mechanism to synchronize local and global model updates, mitigating model drift. We conducted extensive experiments on the VisDrone2019-DET dataset, comparing our method to baseline models. Results demonstrate that our approach accelerates convergence speed by approximately 2.2 times and enhances detection performance by around 3%, offering an efficient and robust solution for UAV-based object detection under non-IID conditions.

The efficient design of biohybrid materials requires controlling the interaction between the cell and the material for a wide range of possible combinations. Single cell force spectroscopy (SCFS), an atomic force microscopy (AFM) experimental procedure based on the binding of an individual cell to an AFM cantilever and the assessment of the adhesion force between the cell and a target substrate, represents one of the most promising alternatives to characterize the interaction between cell and material. However, SCFS relies on the efficient binding of the cell to the AFM in order to avoid drawbacks, such as the detachment of the cell. In this work, three different versatile and robust procedures are presented that allow for the binding of either non-adherent (CD4+ T-lymphocytes) or adherent (mesenchymal stem cells, MSC) cells to the AFM probe. The three crosslinking strategies comprise (1) the streptavidin/biotin system, (2) sulfhydryl group-based crosslinkers, and (3) "click" (bioorthogonal) chemistry. Additionally, three decoration schemes of the functionalized AFM probes are explored: a specific antibody, concanavalin A, and direct binding of the cell through azide-derivatized membrane proteins. Differences are observed between these alternatives and it is found that the strength of the interaction (in decreasing order) is as follows: specific antibody, concanavalin A, and binding through azide-derivatized proteins.

Balancing exploration and exploitation remains a fundamental challenge in reliable mobile robot control, as conventional policies often converge on suboptimal behaviors. Inspired by the brain's division of labor for adaptive control, we propose SpikeAEC, a fully spiking, neuromodulated Actor-Explorer-Critic architecture designed to address this dilemma online within a closed-loop system. SpikeAEC comprises three specialized subnetworks operating in parallel: the Actor, inspired by the basal ganglia, proposes exploitative actions; the Explorer, modeled after the ACC-GPe-STN pathway, generates adaptive exploratory actions gated by a vigilance signal modulated by the accumulated global temporal-difference (TD) error; and the Critic, based on the ventral striatum, computes the TD error. The final action is selected by a separate, TAN-based Arbitrator, which probabilistically chooses between the Actor's and Explorer's action proposals according to recent performance and the TD error. These subnetworks are coupled through a unified three-factor learning framework that uses the TD signal and phasic neuromodulators (acetylcholine and dopamine) from the Arbitrator to drive pathway-specific synaptic plasticity. This online plasticity enhances the quality of action proposals and accelerates policy refinement. In simulation, SpikeAEC outperforms leading brain-inspired methods by converging 24% faster, reducing trajectory length by 18%, and increasing cumulative reward by over 5% against the top-performing baseline, all while maintaining consistency with established neurophysiological principles.

There is broad consensus that successful repair of severe peripheral nerve injuries requires recreating key structural and cellular features of the natural regenerative process, particularly the action of Bands of Büngner (BoB), longitudinal Schwann cell (SC) structures that guide regenerating axons. Current biomaterial-based strategies have shown limited efficacy, in part because they do not sufficiently reproduce the anisotropic and cellular microenvironment established by BoB, resulting in disorganized axonal growth and reduced regenerative efficiency across long gaps. To address this limitation, a biohybrid scaffold designed to promote Schwann cell self-organization into Büngner-like structures through defined physical cues. Rather than relying solely on biochemical supplementation is developed, this system leverages anisotropic fiber architecture to induce SC alignment and early activation-associated phenotypic modulation. In this study, a self-organizing biohybrid BoB (BBoB) construct formed by Schwann cells within an aligned fiber-based scaffold is presented. It is demonstrated that these engineered structures recapitulate key morphological features of native BoB in vitro and promote enhanced axonal regeneration across a 11 mm sciatic nerve defect in vivo. Together, these findings support the concept that physically programmed Schwann cell organization within biomaterial conduits can enhance peripheral nerve regeneration, using clinically accessible biomaterials and autologous Schwann cells.

Recent advances in neural networks have introduced a new paradigm for robotic inverse kinematics. However, existing methods remain limited by insufficient feature extraction and suboptimal integration of multi-source information, preventing them from achieving high accuracy, broad generalization, and real-time performance on robots with diverse and complex kinematic structures. In this work, we propose HarmoAtt-IK, an adaptive multimodal neural inverse kinematics approach designed for real-time inference and zero-collection training. Built upon the CycleIK framework, the proposed method introduces a novel adaptive multimodal attention fusion mechanism (HarmoAtt) that dynamically integrates the complementary strengths of spatial, channel, and cross-dimensional attention. It employs a temperature-adaptive Softmax function coupled with a compact weight-generation network to perform multidimensional extraction and adaptive enhancement of input features. We further introduce a composite loss function integrating an improved Smooth-L1 loss, a sign-invariant quaternion loss, and a Shannon entropy regularizer to enhance training stability and overall accuracy. Leveraging forward differential kinematics, our method enables rapid, cross-platform deployment by generating training data solely from URDF models, eliminating the need for costly physical data collection and manual annotation. Experimental evaluations on five humanoid platforms exhibiting substantial kinematic diversity demonstrate that HarmoAtt-IK attains maximum reductions of 76.4% in terminal positional error and 55.1% in rotational error relative to the baseline, while consistently improving the model's inference success rate across all tested platforms by up to 5.76 percentage points. These results indicate that the proposed HarmoAtt-IK significantly outperforms baseline methods in both accuracy and reliability across diverse kinematic structures, highlighting the effectiveness of the adaptive multimodal attention mechanism and composite loss design. This further supports its potential for scalable, real-time deployment on a wide range of robotic platforms.

Neurodegenerative diseases (NDs) are a significant threat to human health. Numerous research demonstrated that patients with NDs might present with decreased balance, which is responsible for an increased risk of falling. As an emerging technology, wearable devices can detect falls and prevent privacy breaches. To access the evolution of trends and technology in wearable devices to detect falls among patients with NDs. We screened PubMed and Web of Science (February 2023) to summarize the pathway of fall detection with any body-worn sensor. Included articles were required to be full-text and published in English. Documents were excluded if they; (1) only used wearable devices for fall cueing, (2) did not offer sufficient information for data extraction, (3) did not use patients with NDs, (4) only used non-wearable sensors or devices. The review identified 89 articles at the end of the procedure for data extraction. A wide variety existed in participant sample size (1-131), sensor types, placement and algorithms. 97.75% of papers (n = 87) used patients with Parkinson's disease as experimental subjects. 21.45% of studies attached devices on the ankle (n = 19), with a clear preference for using multiple types of sensors (58.43% of studies, n = 52). As the most commonly used inertial measurement unit (IMU), 21 articles utilized accelerometers and gyroscopes to assess falls. 39.33% of studies (n = 35) choose data set to verify the effectiveness of their algorithm. Machine learning algorithms have become prevalent since 2019, and the most commonly used algorithm was support vector machine (SVM) (n = 17). These results show that an increasing number of researchers examine the validation performance of their systems in non-real-time. The ankle was the preferred location among researchers, and there is a clear preference to use multiple types of sensors and machine learning algorithms to improve accuracy and immediacy. Future work should focus on other NDs instead of limiting to Parkinson's disease and consider an adequately studied population. A consensus on walking tasks and accuracy measurements is urgently needed. Performing studies in a simulated free-living environment for a specified time frame is advisable, with continuous real-time monitoring and assessment. PROSPERO, identifier (CRD42023405952).

Objective: This study investigates the neurodynamics of motor imagery speed decoding using deep learning. Methods: The EEGConformer model was employed to analyze EEG signals and decode different speeds of imagined movements. Explainable artificial intelligence techniques were used to identify the temporal and spatial patterns within the EEG data related to imagined speeds, focusing on the role of specific frequency bands and cortical regions. Results: The model successfully decoded and extracted EEG patterns associated with different motor imagery speeds; however, the classification accuracy was limited and high only for a few participants. The analysis highlighted the importance of alpha and beta oscillations and identified key cortical areas, including the frontal, motor, and occipital cortices, in speed decoding. Additionally, repeated motor imagery elicited steady-state movement-related potentials at the fundamental frequency, with the strongest responses observed at the second harmonic. Conclusions: Motor imagery speed is decodable, though classification performance remains limited. The results highlight the involvement of specific frequency bands and cortical regions, as well as steady-state responses, in encoding MI speed.