Frontiers in Neurorobotics最新文献

{"title":"ActionX: pre-training action experts with reinforcement learning for vision-language action models.","authors":"Tinghao Yi, Quantao Yang, Enhong Chen","doi":"10.3389/fnbot.2026.1806605","DOIUrl":"10.3389/fnbot.2026.1806605","url":null,"abstract":"<p><p>Vision-Language Action (VLA) models have enabled language-driven robotic manipulation by integrating language instructions, visual perception, and action generation. However, existing VLA approaches heavily rely on large-scale human demonstration datasets, which leads to substantial data collection and training costs. To address this, we propose ActionX, a pretraining framework that learns Action eXperts using reinforcement learning while leveraging a frozen, pretrained Vision-Language Model (VLM) backbone. The pretrained action expert is then integrated with the vision-language backbone and fine-tuned end-to-end using a small amount of expert data to align perception, language, and action for downstream manipulation tasks. We evaluate ActionX on the LIBERO and Meta-World benchmarks as well as real-world robotic manipulation scenarios. Experimental results show that ActionX achieves +16% success rate compare to state-of-the-art VLA models trained with large-scale demonstrations, while requiring only less than 100 expert demonstrations for real robot tasks for whole training phase. This performance is achieved by establishing an optimized action expert model through reinforcement learning, which significantly enhances VLA training efficiency.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1806605"},"PeriodicalIF":3.5,"publicationDate":"2026-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13121100/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147769541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trainable movement control using spikes and muscle-twitch dynamics.","authors":"Jordi Timmermans, Lambert Schomaker","doi":"10.3389/fnbot.2026.1761767","DOIUrl":"10.3389/fnbot.2026.1761767","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1761767"},"PeriodicalIF":3.5,"publicationDate":"2026-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13111196/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147769477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal human action recognition and personalized sports health promotion: a deep learning framework integrating wearable sensor fusion.","authors":"Ying Xi, Taibin Huang, Zhiyu Yang","doi":"10.3389/fnbot.2026.1785114","DOIUrl":"10.3389/fnbot.2026.1785114","url":null,"abstract":"<p><strong>Introduction: </strong>In real-world sports scenarios, Human Action Recognition (HAR) is often hindered by data complexity, limited dynamic adaptability, and fragmented integration of physiological and kinematic information. To address these challenges, this study proposes a multimodal HAR framework for personalized sports health promotion by integrating wearable sensor streams with deep learning architectures.</p><p><strong>Methods: </strong>The proposed system employs a robust sensing layer to capture 12-dimensional multimodal data and synchronize physiological indicators with behavioral signals in real time. A novel Transformer-GCN hybrid model was developed to extract complex spatiotemporal dependencies for accurate action recognition and dynamic state analysis. In addition, a reinforcement learning module was incorporated to generate adaptive exercise prescriptions based on user progress. The framework was deployed through a responsive interface for real-time intervention and evaluated in a 12-week randomized controlled trial.</p><p><strong>Results: </strong>The results demonstrated that the proposed framework achieved effective multimodal fusion and reliable action recognition in sports scenarios. After the 12-week intervention, participants in the intervention group showed a 20.1% increase in cardiorespiratory fitness (<i>VO</i> ₂ max), a 99.3% improvement in muscular endurance, and a sports injury rate maintained below 15%. These findings indicate that the framework can support accurate motion analysis and safe, personalized intervention.</p><p><strong>Discussion: </strong>The proposed multimodal fusion architecture effectively bridges the gap between action recognition and personalized sports health intervention. By combining wearable sensing, hybrid deep learning, and reinforcement learning, the framework provides a practical solution for AI-driven motion analysis and adaptive health promotion in land sports scenarios.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1785114"},"PeriodicalIF":3.5,"publicationDate":"2026-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13106161/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147769513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Enhancing 3D semantic scene completion with refinement module.","authors":"","doi":"10.3389/fnbot.2026.1838975","DOIUrl":"10.3389/fnbot.2026.1838975","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.3389/fnbot.2026.1768219.].</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1838975"},"PeriodicalIF":3.5,"publicationDate":"2026-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13096882/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147769547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Neurorobotics for automotive manufacturing industry in era of embodied intelligence: a mini review.","authors":"Bangcheng Zhang, Qi Xia","doi":"10.3389/fnbot.2026.1829525","DOIUrl":"10.3389/fnbot.2026.1829525","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.3389/fnbot.2026.1796043.].</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1829525"},"PeriodicalIF":3.5,"publicationDate":"2026-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13085049/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147722539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust federated learning for UAV object detection: a joint self-distillation and drift compensation approach.","authors":"Yu Hangsun, Changnan Jiang, Ziyuan Zhang, Heqing Ouyang, Pengpeng Chen","doi":"10.3389/fnbot.2026.1649168","DOIUrl":"10.3389/fnbot.2026.1649168","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1649168"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13079609/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147698262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Constructing three-way classifier with interval granulation neighborhood rough sets based on uncertainty invariance.","authors":"Yongqi Wang, Taihua Xu, Rong Huang, Zhuangzhuang Liu, Jie Yang","doi":"10.3389/fnbot.2026.1787501","DOIUrl":"10.3389/fnbot.2026.1787501","url":null,"abstract":"<p><p>Three-way decision with neighborhood rough sets (3WDNRS) is effective in handling uncertain problems involving continuous data through the adjustment of the neighborhood radius. However, it faces two main limitations. Firstly, 3WDNRS relies on individual neighborhood granules as inputs, which can impair both decision efficiency and model generalizability. Secondly, the thresholds used in 3WDNRS often require predefinition based on prior knowledge, making the method difficult to apply in situations where such knowledge is lacking. To address these problems, this study introduces interval granulation (IG) into 3WD to construct an effective three-way classifier. Firstly, an interval granulation method based on DBSCAN is proposed. Then, an interval granulation neighborhood rough sets (IGNRS) model is presented, combining IG with quality indicators. Based on the IGNRS, a three-way classifier called 3WD-IGNRS is proposed by considering the principle of minimum fuzzy loss. Finally, extensive comparative experiments are conducted with three state-of-the-art granular-ball (GB)-based classifiers and four classical machine learning classifiers on 12 public benchmark datasets. The results demonstrate that our models consistently outperform the compared methods, achieving an average accuracy improvement of 4.94% compared to the best-performing granular-ball classifier.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1787501"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13079323/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147697736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A brain-inspired ISMO-PNN framework for neurally-grounded bearing fault diagnosis.","authors":"Fan Zhang, Bangcheng Zhang","doi":"10.3389/fnbot.2026.1807995","DOIUrl":"10.3389/fnbot.2026.1807995","url":null,"abstract":"<p><strong>Introduction: </strong>In advanced robot systems, monitoring the health of key components such as bearings in the transmission system is crucial for achieving reliable autonomous operation. However, there are still challenges in accurately diagnosing bearing faults under dynamic and noisy conditions.</p><p><strong>Methods: </strong>To address this issue, this paper propose a brain-inspired computational framework that integrates an Improved Spider Monkey Optimization algorithm with a Probabilistic Neural Network (ISMO-PNN) for neurally-grounded bearing fault diagnosis in robotic systems. The main content includes: (1) extracting a 22 dimensional mixed feature set from vibration signals, (2) using intelligent PCA strategy to reduce the dimensionality of features to three dimensions while retaining more than 80% of the discriminative information, and (3) using ISMO algorithm to automatically optimize the key smoothing parameters of PNN.</p><p><strong>Results: </strong>On the CWRU bearing dataset, the ISMO-PNN model has a fault classification accuracy of 97.14% and a macro-average F1 score of 97.32%, which is superior to other comparative models in the article. In addition, the minimum training and testing accuracy difference of the model is 0.72%, indicating strong generalization ability.</p><p><strong>Discussion: </strong>This brain-inspired framework, synergizing a neurally-grounded probabilistic classifier with a bio-inspired swarm optimizer, forms a robust and efficient embedded health monitoring model, which can provide feasible solutions for the development of advanced robot systems.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1807995"},"PeriodicalIF":3.5,"publicationDate":"2026-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13047198/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147622723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Multi-modal learning with large-scale models.","authors":"Xianmin Wang, Jing Li","doi":"10.3389/fnbot.2026.1816779","DOIUrl":"10.3389/fnbot.2026.1816779","url":null,"abstract":"","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1816779"},"PeriodicalIF":2.8,"publicationDate":"2026-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13021788/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147573616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The evolution of trends and technology in wearable sensors used to detect falls in people with neurodegenerative diseases: a systematic review.","authors":"Yuanzheng Chen, Tinghuai Huang, Zijie Lin, Quan Zhou","doi":"10.3389/fnbot.2026.1766109","DOIUrl":"10.3389/fnbot.2026.1766109","url":null,"abstract":"<p><strong>Background: </strong>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.</p><p><strong>Objective: </strong>To access the evolution of trends and technology in wearable devices to detect falls among patients with NDs.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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 (<i>n</i> = 87) used patients with Parkinson's disease as experimental subjects. 21.45% of studies attached devices on the ankle (<i>n</i> = 19), with a clear preference for using multiple types of sensors (58.43% of studies, <i>n</i> = 52). As the most commonly used inertial measurement unit (IMU), 21 articles utilized accelerometers and gyroscopes to assess falls. 39.33% of studies (<i>n</i> = 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) (<i>n</i> = 17).</p><p><strong>Conclusion: </strong>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.</p><p><strong>Systematic review registration: </strong>PROSPERO, identifier (CRD42023405952).</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1766109"},"PeriodicalIF":3.5,"publicationDate":"2026-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13021662/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147573608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}