Pub Date : 2024-10-31eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1453061
An Jianliang
Introduction: With the development of artificial intelligence and robotics technology, the application of educational robots in teaching is becoming increasingly popular. However, effectively evaluating and optimizing multimodal educational robots remains a challenge.
Methods: This study introduces Res-ALBEF, a multimodal educational robot framework driven by dynamic attention. Res-ALBEF enhances the ALBEF (Align Before Fuse) method by incorporating residual connections to align visual and textual data more effectively before fusion. In addition, the model integrates a VGG19-based convolutional network for image feature extraction and utilizes a dynamic attention mechanism to dynamically focus on relevant parts of multimodal inputs. Our model was trained using a diverse dataset consisting of 50,000 multimodal educational instances, covering a variety of subjects and instructional content.
Results and discussion: The evaluation on an independent validation set of 10,000 samples demonstrated significant performance improvements: the model achieved an overall accuracy of 97.38% in educational content recognition. These results highlight the model's ability to improve alignment and fusion of multimodal information, making it a robust solution for multimodal educational robots.
{"title":"A multimodal educational robots driven via dynamic attention.","authors":"An Jianliang","doi":"10.3389/fnbot.2024.1453061","DOIUrl":"10.3389/fnbot.2024.1453061","url":null,"abstract":"<p><strong>Introduction: </strong>With the development of artificial intelligence and robotics technology, the application of educational robots in teaching is becoming increasingly popular. However, effectively evaluating and optimizing multimodal educational robots remains a challenge.</p><p><strong>Methods: </strong>This study introduces Res-ALBEF, a multimodal educational robot framework driven by dynamic attention. Res-ALBEF enhances the ALBEF (Align Before Fuse) method by incorporating residual connections to align visual and textual data more effectively before fusion. In addition, the model integrates a VGG19-based convolutional network for image feature extraction and utilizes a dynamic attention mechanism to dynamically focus on relevant parts of multimodal inputs. Our model was trained using a diverse dataset consisting of 50,000 multimodal educational instances, covering a variety of subjects and instructional content.</p><p><strong>Results and discussion: </strong>The evaluation on an independent validation set of 10,000 samples demonstrated significant performance improvements: the model achieved an overall accuracy of 97.38% in educational content recognition. These results highlight the model's ability to improve alignment and fusion of multimodal information, making it a robust solution for multimodal educational robots.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1453061"},"PeriodicalIF":2.6,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11560911/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142618559","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}
Pub Date : 2024-10-31eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1457843
Dong Chen, Peisong Wu, Mingdong Chen, Mengtao Wu, Tao Zhang, Chuanqi Li
Over the past few years, a growing number of researchers have dedicated their efforts to focusing on temporal modeling. The advent of transformer-based methods has notably advanced the field of 2D image-based vision tasks. However, with respect to 3D video tasks such as action recognition, applying temporal transformations directly to video data significantly increases both computational and memory demands. This surge in resource consumption is due to the multiplication of data patches and the added complexity of self-aware computations. Accordingly, building efficient and precise 3D self-attentive models for video content represents as a major challenge for transformers. In our research, we introduce an Long and Short-term Temporal Difference Vision Transformer (LS-VIT). This method incorporates short-term motion details into images by weighting the difference across several consecutive frames, thereby equipping the original image with the ability to model short-term motions. Concurrently, we integrate a module designed to understand long-term motion details. This module enhances the model's capacity for long-term motion modeling by directly integrating temporal differences from various segments via motion excitation. Our thorough analysis confirms that the LS-VIT achieves high recognition accuracy across multiple benchmarks (e.g., UCF101, HMDB51, Kinetics-400). These research results indicate that LS-VIT has the potential for further optimization, which can improve real-time performance and action prediction capabilities.
{"title":"LS-VIT: Vision Transformer for action recognition based on long and short-term temporal difference.","authors":"Dong Chen, Peisong Wu, Mingdong Chen, Mengtao Wu, Tao Zhang, Chuanqi Li","doi":"10.3389/fnbot.2024.1457843","DOIUrl":"10.3389/fnbot.2024.1457843","url":null,"abstract":"<p><p>Over the past few years, a growing number of researchers have dedicated their efforts to focusing on temporal modeling. The advent of transformer-based methods has notably advanced the field of 2D image-based vision tasks. However, with respect to 3D video tasks such as action recognition, applying temporal transformations directly to video data significantly increases both computational and memory demands. This surge in resource consumption is due to the multiplication of data patches and the added complexity of self-aware computations. Accordingly, building efficient and precise 3D self-attentive models for video content represents as a major challenge for transformers. In our research, we introduce an Long and Short-term Temporal Difference Vision Transformer (LS-VIT). This method incorporates short-term motion details into images by weighting the difference across several consecutive frames, thereby equipping the original image with the ability to model short-term motions. Concurrently, we integrate a module designed to understand long-term motion details. This module enhances the model's capacity for long-term motion modeling by directly integrating temporal differences from various segments via motion excitation. Our thorough analysis confirms that the LS-VIT achieves high recognition accuracy across multiple benchmarks (e.g., UCF101, HMDB51, Kinetics-400). These research results indicate that LS-VIT has the potential for further optimization, which can improve real-time performance and action prediction capabilities.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1457843"},"PeriodicalIF":2.6,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11560894/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142618575","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}
Pub Date : 2024-10-31eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1443010
Haneen Alsuradi, Joseph Hong, Helin Mazi, Mohamad Eid
Wearable augmentations (WAs) designed for movement and manipulation, such as exoskeletons and supernumerary robotic limbs, are used to enhance the physical abilities of healthy individuals and substitute or restore lost functionality for impaired individuals. Non-invasive neuro-motor (NM) technologies, including electroencephalography (EEG) and sufrace electromyography (sEMG), promise direct and intuitive communication between the brain and the WA. After presenting a historical perspective, this review proposes a conceptual model for NM-controlled WAs, analyzes key design aspects, such as hardware design, mounting methods, control paradigms, and sensory feedback, that have direct implications on the user experience, and in the long term, on the embodiment of WAs. The literature is surveyed and categorized into three main areas: hand WAs, upper body WAs, and lower body WAs. The review concludes by highlighting the primary findings, challenges, and trends in NM-controlled WAs. This review motivates researchers and practitioners to further explore and evaluate the development of WAs, ensuring a better quality of life.
为运动和操纵而设计的可穿戴增强装置(WA),如外骨骼和编外机器人肢体,可用于增强健康人的体能,替代或恢复受损人失去的功能。非侵入性神经运动(NM)技术,包括脑电图(EEG)和超声肌电图(sEMG),有望在大脑和WA之间实现直接而直观的交流。在介绍了历史视角之后,本综述提出了一个由 NM 控制的 WA 概念模型,分析了关键的设计方面,如硬件设计、安装方法、控制范例和感觉反馈,这些方面对用户体验有直接影响,从长远来看,对 WA 的体现有直接影响。文献概览分为三个主要领域:手部 WA、上半身 WA 和下半身 WA。综述最后强调了由 NM 控制的 WA 的主要发现、挑战和趋势。本综述激励研究人员和从业人员进一步探索和评估 WAs 的发展,以确保更好的生活质量。
{"title":"Neuro-motor controlled wearable augmentations: current research and emerging trends.","authors":"Haneen Alsuradi, Joseph Hong, Helin Mazi, Mohamad Eid","doi":"10.3389/fnbot.2024.1443010","DOIUrl":"10.3389/fnbot.2024.1443010","url":null,"abstract":"<p><p>Wearable augmentations (WAs) designed for movement and manipulation, such as exoskeletons and supernumerary robotic limbs, are used to enhance the physical abilities of healthy individuals and substitute or restore lost functionality for impaired individuals. Non-invasive neuro-motor (NM) technologies, including electroencephalography (EEG) and sufrace electromyography (sEMG), promise direct and intuitive communication between the brain and the WA. After presenting a historical perspective, this review proposes a conceptual model for NM-controlled WAs, analyzes key design aspects, such as hardware design, mounting methods, control paradigms, and sensory feedback, that have direct implications on the user experience, and in the long term, on the embodiment of WAs. The literature is surveyed and categorized into three main areas: hand WAs, upper body WAs, and lower body WAs. The review concludes by highlighting the primary findings, challenges, and trends in NM-controlled WAs. This review motivates researchers and practitioners to further explore and evaluate the development of WAs, ensuring a better quality of life.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1443010"},"PeriodicalIF":2.6,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11560910/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142618577","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}
Pub Date : 2024-10-29eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1503038
Paloma de la Puente, Markus Vincze, Diego Guffanti, Daniel Galan
{"title":"Editorial: Assistive and service robots for health and home applications (RH3 - Robot Helpers in Health and Home).","authors":"Paloma de la Puente, Markus Vincze, Diego Guffanti, Daniel Galan","doi":"10.3389/fnbot.2024.1503038","DOIUrl":"https://doi.org/10.3389/fnbot.2024.1503038","url":null,"abstract":"","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1503038"},"PeriodicalIF":2.6,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11554614/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142618571","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}
Pub Date : 2024-10-22eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1488337
Lei Wang, Danping Liu, Jun Wang
Ensuring representativeness of collected samples is the most critical requirement of water sampling. Unmanned surface vehicles (USVs) have been widely adopted in water sampling, but current USV sampling path planning tend to overemphasize path optimization, neglecting the representative samples collection. This study proposed a modified A* algorithm that combined remote sensing technique while considering both path length and the representativeness of collected samples. Water quality parameters were initially retrieved using satellite remote sensing imagery and a deep belief network model, with the parameter value incorporated as coefficient Q in the heuristic function of A* algorithm. The adjustment coefficient k was then introduced into the coefficient Q to optimize the trade-off between sampling representativeness and path length. To evaluate the effectiveness of this algorithm, Chlorophyll-a concentration (Chl-a) was employed as the test parameter, with Chaohu Lake as the study area. Results showed that the algorithm was effective in collecting more representative samples in real-world conditions. As the coefficient k increased, the representativeness of collected samples enhanced, indicated by the Chl-a closely approximating the overall mean Chl-a and exhibiting a gradient distribution. This enhancement was also associated with increased path length. This study is significant in USV water sampling and water environment protection.
{"title":"A modified A* algorithm combining remote sensing technique to collect representative samples from unmanned surface vehicles.","authors":"Lei Wang, Danping Liu, Jun Wang","doi":"10.3389/fnbot.2024.1488337","DOIUrl":"10.3389/fnbot.2024.1488337","url":null,"abstract":"<p><p>Ensuring representativeness of collected samples is the most critical requirement of water sampling. Unmanned surface vehicles (USVs) have been widely adopted in water sampling, but current USV sampling path planning tend to overemphasize path optimization, neglecting the representative samples collection. This study proposed a modified A* algorithm that combined remote sensing technique while considering both path length and the representativeness of collected samples. Water quality parameters were initially retrieved using satellite remote sensing imagery and a deep belief network model, with the parameter value incorporated as coefficient <i>Q</i> in the heuristic function of A* algorithm. The adjustment coefficient <i>k</i> was then introduced into the coefficient <i>Q</i> to optimize the trade-off between sampling representativeness and path length. To evaluate the effectiveness of this algorithm, Chlorophyll-a concentration (Chl-a) was employed as the test parameter, with Chaohu Lake as the study area. Results showed that the algorithm was effective in collecting more representative samples in real-world conditions. As the coefficient <i>k</i> increased, the representativeness of collected samples enhanced, indicated by the Chl-a closely approximating the overall mean Chl-a and exhibiting a gradient distribution. This enhancement was also associated with increased path length. This study is significant in USV water sampling and water environment protection.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1488337"},"PeriodicalIF":2.6,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11535655/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142582574","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}
Pub Date : 2024-10-21eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1443177
Libo Ma, Yan Tong
Currently, the application of robotics technology in sports training and competitions is rapidly increasing. Traditional methods mainly rely on image or video data, neglecting the effective utilization of textual information. To address this issue, we propose: TL-CStrans Net: A vision robot for table tennis player action recognition driven via CS-Transformer. This is a multimodal approach that combines CS-Transformer, CLIP, and transfer learning techniques to effectively integrate visual and textual information. Firstly, we employ the CS-Transformer model as the neural computing backbone. By utilizing the CS-Transformer, we can effectively process visual information extracted from table tennis game scenes, enabling accurate stroke recognition. Then, we introduce the CLIP model, which combines computer vision and natural language processing. CLIP allows us to jointly learn representations of images and text, thereby aligning the visual and textual modalities. Finally, to reduce training and computational requirements, we leverage pre-trained CS-Transformer and CLIP models through transfer learning, which have already acquired knowledge from relevant domains, and apply them to table tennis stroke recognition tasks. Experimental results demonstrate the outstanding performance of TL-CStrans Net in table tennis stroke recognition. Our research is of significant importance in promoting the application of multimodal robotics technology in the field of sports and bridging the gap between neural computing, computer vision, and neuroscience.
{"title":"TL-CStrans Net: a vision robot for table tennis player action recognition driven via CS-Transformer.","authors":"Libo Ma, Yan Tong","doi":"10.3389/fnbot.2024.1443177","DOIUrl":"10.3389/fnbot.2024.1443177","url":null,"abstract":"<p><p>Currently, the application of robotics technology in sports training and competitions is rapidly increasing. Traditional methods mainly rely on image or video data, neglecting the effective utilization of textual information. To address this issue, we propose: TL-CStrans Net: A vision robot for table tennis player action recognition driven via CS-Transformer. This is a multimodal approach that combines CS-Transformer, CLIP, and transfer learning techniques to effectively integrate visual and textual information. Firstly, we employ the CS-Transformer model as the neural computing backbone. By utilizing the CS-Transformer, we can effectively process visual information extracted from table tennis game scenes, enabling accurate stroke recognition. Then, we introduce the CLIP model, which combines computer vision and natural language processing. CLIP allows us to jointly learn representations of images and text, thereby aligning the visual and textual modalities. Finally, to reduce training and computational requirements, we leverage pre-trained CS-Transformer and CLIP models through transfer learning, which have already acquired knowledge from relevant domains, and apply them to table tennis stroke recognition tasks. Experimental results demonstrate the outstanding performance of TL-CStrans Net in table tennis stroke recognition. Our research is of significant importance in promoting the application of multimodal robotics technology in the field of sports and bridging the gap between neural computing, computer vision, and neuroscience.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1443177"},"PeriodicalIF":2.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11532032/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142575211","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}
Pub Date : 2024-10-21eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1508032
[This corrects the article DOI: 10.3389/fnbot.2024.1452019.].
[此处更正了文章 DOI:10.3389/fnbot.2024.1452019.]。
{"title":"Erratum: Swimtrans Net: a multimodal robotic system for swimming action recognition driven via Swin-Transformer.","authors":"","doi":"10.3389/fnbot.2024.1508032","DOIUrl":"https://doi.org/10.3389/fnbot.2024.1508032","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.3389/fnbot.2024.1452019.].</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1508032"},"PeriodicalIF":2.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11551536/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142618573","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}
Panoptic segmentation plays a crucial role in enabling robots to comprehend their surroundings, providing fine-grained scene understanding information for robots' intelligent tasks. Although existing methods have made some progress, they are prone to fail in areas with weak textures, small objects, etc. Inspired by biological vision research, we propose a cascaded contour-enhanced panoptic segmentation network called CCPSNet, attempting to enhance the discriminability of instances through structural knowledge. To acquire the scene structure, a cascade contour detection stream is designed, which extracts comprehensive scene contours using channel regulation structural perception module and coarse-to-fine cascade strategy. Furthermore, the contour-guided multi-scale feature enhancement stream is developed to boost the discrimination ability for small objects and weak textures. The stream integrates contour information and multi-scale context features through structural-aware feature modulation module and inverse aggregation technique. Experimental results show that our method improves accuracy on the Cityscapes (61.2 PQ) and COCO (43.5 PQ) datasets while also demonstrating robustness in challenging simulated real-world complex scenarios faced by robots, such as dirty cameras and rainy conditions. The proposed network promises to help the robot perceive the real scene. In future work, an unsupervised training strategy for the network could be explored to reduce the training cost.
{"title":"Cascade contour-enhanced panoptic segmentation for robotic vision perception.","authors":"Yue Xu, Runze Liu, Dongchen Zhu, Lili Chen, Xiaolin Zhang, Jiamao Li","doi":"10.3389/fnbot.2024.1489021","DOIUrl":"10.3389/fnbot.2024.1489021","url":null,"abstract":"<p><p>Panoptic segmentation plays a crucial role in enabling robots to comprehend their surroundings, providing fine-grained scene understanding information for robots' intelligent tasks. Although existing methods have made some progress, they are prone to fail in areas with weak textures, small objects, etc. Inspired by biological vision research, we propose a cascaded contour-enhanced panoptic segmentation network called CCPSNet, attempting to enhance the discriminability of instances through structural knowledge. To acquire the scene structure, a cascade contour detection stream is designed, which extracts comprehensive scene contours using channel regulation structural perception module and coarse-to-fine cascade strategy. Furthermore, the contour-guided multi-scale feature enhancement stream is developed to boost the discrimination ability for small objects and weak textures. The stream integrates contour information and multi-scale context features through structural-aware feature modulation module and inverse aggregation technique. Experimental results show that our method improves accuracy on the Cityscapes (61.2 PQ) and COCO (43.5 PQ) datasets while also demonstrating robustness in challenging simulated real-world complex scenarios faced by robots, such as dirty cameras and rainy conditions. The proposed network promises to help the robot perceive the real scene. In future work, an unsupervised training strategy for the network could be explored to reduce the training cost.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1489021"},"PeriodicalIF":2.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11532083/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577450","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}
Pub Date : 2024-10-18eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1477232
Zhiquan Chen, Jiabao Guo, Yishan Liu, Mengqian Tian, Xingsong Wang
In this work, the mechanical principles of external fixation and resistance training for the wrist affected by a distal radius fracture (DRF) are revealed. Based on the biomechanical analysis, two wearable exoskeleton devices are proposed to facilitate the DRF rehabilitation progress. Chronologically, the adjustable fixation device (AFD) provides fixed protection and limited mobilization of the fractured wrist in the early stage, while the functional recovery of relevant muscles is achieved by the resistance training device (RTD) in the later stage. According to the designed mechatronic systems of AFD and RTD, the experimental prototypes for these two apparatuses are established. By experiments, the actual motion ranges of AFD are investigated, and the feasibility in monitoring joint angles are validated. Meanwhile, the resistant influences of RTD are analyzed based on the surface electromyography (sEMG) signal features, the results demonstrate that the training-induced muscle strength enhancement is generally increased with the increment in external resistance. The exoskeleton devices presented in this work would be beneficial for the active rehabilitation of patients with DRF.
{"title":"Design and analysis of exoskeleton devices for rehabilitation of distal radius fracture.","authors":"Zhiquan Chen, Jiabao Guo, Yishan Liu, Mengqian Tian, Xingsong Wang","doi":"10.3389/fnbot.2024.1477232","DOIUrl":"10.3389/fnbot.2024.1477232","url":null,"abstract":"<p><p>In this work, the mechanical principles of external fixation and resistance training for the wrist affected by a distal radius fracture (DRF) are revealed. Based on the biomechanical analysis, two wearable exoskeleton devices are proposed to facilitate the DRF rehabilitation progress. Chronologically, the adjustable fixation device (AFD) provides fixed protection and limited mobilization of the fractured wrist in the early stage, while the functional recovery of relevant muscles is achieved by the resistance training device (RTD) in the later stage. According to the designed mechatronic systems of AFD and RTD, the experimental prototypes for these two apparatuses are established. By experiments, the actual motion ranges of AFD are investigated, and the feasibility in monitoring joint angles are validated. Meanwhile, the resistant influences of RTD are analyzed based on the surface electromyography (sEMG) signal features, the results demonstrate that the training-induced muscle strength enhancement is generally increased with the increment in external resistance. The exoskeleton devices presented in this work would be beneficial for the active rehabilitation of patients with DRF.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1477232"},"PeriodicalIF":2.6,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11527727/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142570965","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}
Pub Date : 2024-10-14eCollection Date: 2024-01-01DOI: 10.3389/fnbot.2024.1484088
Zixin Huang, Xuesong Tao, Xinyuan Liu
Object detection plays a crucial role in robotic vision, focusing on accurately identifying and localizing objects within images. However, many existing methods encounter limitations, particularly when it comes to effectively implementing a one-to-many matching strategy. To address these challenges, we propose NAN-DETR (Noising Multi-Anchor Detection Transformer), an innovative framework based on DETR (Detection Transformer). NAN-DETR introduces three key improvements to transformer-based object detection: a decoder-based multi-anchor strategy, a centralization noising mechanism, and the integration of Complete Intersection over Union (CIoU) loss. The multi-anchor strategy leverages multiple anchors per object, significantly enhancing detection accuracy by improving the one-to-many matching process. The centralization noising mechanism mitigates conflicts among anchors by injecting controlled noise into the detection boxes, thereby increasing the robustness of the model. Additionally, CIoU loss, which incorporates both aspect ratio and spatial distance in its calculations, results in more precise bounding box predictions compared to the conventional IoU loss. Although NAN-DETR may not drastically improve real-time processing capabilities, its exceptional performance positions it as a highly reliable solution for diverse object detection scenarios.
{"title":"NAN-DETR: noising multi-anchor makes DETR better for object detection.","authors":"Zixin Huang, Xuesong Tao, Xinyuan Liu","doi":"10.3389/fnbot.2024.1484088","DOIUrl":"10.3389/fnbot.2024.1484088","url":null,"abstract":"<p><p>Object detection plays a crucial role in robotic vision, focusing on accurately identifying and localizing objects within images. However, many existing methods encounter limitations, particularly when it comes to effectively implementing a one-to-many matching strategy. To address these challenges, we propose NAN-DETR (Noising Multi-Anchor Detection Transformer), an innovative framework based on DETR (Detection Transformer). NAN-DETR introduces three key improvements to transformer-based object detection: a decoder-based multi-anchor strategy, a centralization noising mechanism, and the integration of Complete Intersection over Union (CIoU) loss. The multi-anchor strategy leverages multiple anchors per object, significantly enhancing detection accuracy by improving the one-to-many matching process. The centralization noising mechanism mitigates conflicts among anchors by injecting controlled noise into the detection boxes, thereby increasing the robustness of the model. Additionally, CIoU loss, which incorporates both aspect ratio and spatial distance in its calculations, results in more precise bounding box predictions compared to the conventional IoU loss. Although NAN-DETR may not drastically improve real-time processing capabilities, its exceptional performance positions it as a highly reliable solution for diverse object detection scenarios.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1484088"},"PeriodicalIF":2.6,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11513373/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142521681","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}