Biomimetic Intelligence and Robotics最新文献_第8页

Cooperative search for moving targets with the ability to perceive and evade using multiple UAVs 使用多架无人机对移动目标进行协同搜索，具有感知和逃避的能力

Biomimetic Intelligence and Robotics Pub Date : 2023-10-28 DOI: 10.20517/ir.2023.30

Ziyi Wang, Jian Guo, Wencheng Zou, Sheng Li

{"title":"Cooperative search for moving targets with the ability to perceive and evade using multiple UAVs","authors":"Ziyi Wang, Jian Guo, Wencheng Zou, Sheng Li","doi":"10.20517/ir.2023.30","DOIUrl":"https://doi.org/10.20517/ir.2023.30","url":null,"abstract":"This paper focuses on the problem of regional cooperative search using multiple unmanned aerial vehicles (UAVs) for targets that have the ability to perceive and evade. When UAVs search for moving targets in a mission area, the targets can perceive the positions and flight direction of UAVs within certain limits and take corresponding evasive actions, which makes the search more challenging than traditional search problems. To address this problem, we first define a detailed motion model for such targets and design various search information maps and their update methods to describe the environmental information based on the prediction of moving targets and the search results of UAVs. We then establish a multi-UAV search path planning optimization model based on the model predictive control, which includes various newly designed objective functions of search benefits and costs. We propose a priority-encoded improved genetic algorithm with a fine-adjustment mechanism to solve this model. The simulation results show that the proposed method can effectively improve the cooperative search efficiency, and more targets can be found at a much faster rate compared to traditional search methods.","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"30 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136231823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Large language models for human–robot interaction: A review 人机交互的大型语言模型:综述

Biomimetic Intelligence and Robotics Pub Date : 2023-10-28 DOI: 10.1016/j.birob.2023.100131

Ceng Zhang , Junxin Chen , Jiatong Li , Yanhong Peng , Zebing Mao

{"title":"Large language models for human–robot interaction: A review","authors":"Ceng Zhang , Junxin Chen , Jiatong Li , Yanhong Peng , Zebing Mao","doi":"10.1016/j.birob.2023.100131","DOIUrl":"10.1016/j.birob.2023.100131","url":null,"abstract":"<div><p>The fusion of large language models and robotic systems has introduced a transformative paradigm in human–robot interaction, offering unparalleled capabilities in natural language understanding and task execution. This review paper offers a comprehensive analysis of this nascent but rapidly evolving domain, spotlighting the recent advances of Large Language Models (LLMs) in enhancing their structures and performances, particularly in terms of multimodal input handling, high-level reasoning, and plan generation. Moreover, it probes the current methodologies that integrate LLMs into robotic systems for complex task completion, from traditional probabilistic models to the utilization of value functions and metrics for optimal decision-making. Despite these advancements, the paper also reveals the formidable challenges that confront the field, such as contextual understanding, data privacy and ethical considerations. To our best knowledge, this is the first study to comprehensively analyze the advances and considerations of LLMs in Human–Robot Interaction (HRI) based on recent progress, which provides potential avenues for further research.</p></div>","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"3 4","pages":"Article 100131"},"PeriodicalIF":0.0,"publicationDate":"2023-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667379723000451/pdfft?md5=af36e667ec63efae63765b692d7a9e91&pid=1-s2.0-S2667379723000451-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136160534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Muscle synergy analysis for gesture recognition based on sEMG images and Shapley value 基于肌电图和Shapley值的手势识别肌肉协同分析

Biomimetic Intelligence and Robotics Pub Date : 2023-10-24 DOI: 10.20517/ir.2023.28

Xiaohu Ao, Feng Wang, Rennong Wang, Jinhua She

{"title":"Muscle synergy analysis for gesture recognition based on sEMG images and Shapley value","authors":"Xiaohu Ao, Feng Wang, Rennong Wang, Jinhua She","doi":"10.20517/ir.2023.28","DOIUrl":"https://doi.org/10.20517/ir.2023.28","url":null,"abstract":"Muscle synergy analysis for gesture recognition is a fundamental research area in human-machine interaction, particularly in fields such as rehabilitation. However, previous methods for analyzing muscle synergy are typically not end-to-end and lack interpretability. Specifically, these methods involve extracting specific features for gesture recognition from surface electromyography (sEMG) signals and then conducting muscle synergy analysis based on those features. Addressing these limitations, we devised an end-to-end framework, namely Shapley-value-based muscle synergy (SVMS), for muscle synergy analysis. Our approach involves converting sEMG signals into grayscale sEMG images using a sliding window. Subsequently, we convert adjacent grayscale images into color images for gesture recognition. We then use the gradient-weighted class activation mapping (Grad-CAM) method to identify significant feature areas for sEMG images during gesture recognition. Grad-CAM generates a heatmap representation of the images, highlighting the regions that the model uses to make its prediction. Finally, we conduct a quantitative analysis of muscle synergy in the specific area obtained by Grad-CAM based on the Shapley value. The experimental results demonstrate the effectiveness of our SVMS method for muscle synergy analysis. Moreover, we are able to achieve a recognition accuracy of 94.26% for twelve gestures while reducing the required electrode channel information from ten to six dimensions and the analysis rounds from about 1000 to nine.","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"61 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135321783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Preoperative virtual reduction method for pelvic fractures based on statistical shape models and partial surface data 基于统计形状模型和部分表面数据的骨盆骨折术前虚拟复位方法

Biomimetic Intelligence and Robotics Pub Date : 2023-10-20 DOI: 10.1016/j.birob.2023.100130

Wei Kou , Yaoyao He , Xiao Cheng , Zhewei Wang , Yuan Yang , Shaolong Kuang

{"title":"Preoperative virtual reduction method for pelvic fractures based on statistical shape models and partial surface data","authors":"Wei Kou , Yaoyao He , Xiao Cheng , Zhewei Wang , Yuan Yang , Shaolong Kuang","doi":"10.1016/j.birob.2023.100130","DOIUrl":"https://doi.org/10.1016/j.birob.2023.100130","url":null,"abstract":"<div><p>Virtual reduction is crucial for successful and accurate reduction of pelvic fractures. Various methods have been proposed in this regard. However, not all of them are applicable to every pelvic fracture. Among these methods, the efficiency and accuracy of the method based on statistical shape models in clinical applications require further improvement. This study proposes a virtual reduction method for pelvic fractures that uses statistical shape models and partial surface data of a broken pelvis. Simulated fracture and clinical case experiments were conducted to validate the accuracy and effectiveness of the proposed method. The simulated fracture experiments yielded an average error of 1.57 ± 0.39 mm and a maximum error of 12.82 ± 3.54 mm. The virtual reduction procedure takes approximately 40 s. Based on three clinical case experiments, the proposed method achieves an acceptable level of accuracy compared with manual reduction by a surgeon. The proposed method offers the advantages of shorter virtual reduction times and satisfactory reduction accuracy. In the future, it will be integrated into the preoperative planning system for pelvic fracture reduction, thereby improving patient outcomes.</p></div>","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"3 4","pages":"Article 100130"},"PeriodicalIF":0.0,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266737972300044X/pdfft?md5=ed904a2f8c3ccdc8eab16a43963b8eff&pid=1-s2.0-S266737972300044X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134663214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Visual servoing-based pneumatic hair transplantation mechanism for robotic FUE surgery 基于视觉伺服的机器人FUE手术气动植发机构

Biomimetic Intelligence and Robotics Pub Date : 2023-10-10 DOI: 10.1016/j.birob.2023.100128

Fulin Jia, Shenghao Yang, Chenxi Han, Junye Li, Xuanru Han, Chao Zhang, Jiaole Wang

{"title":"Visual servoing-based pneumatic hair transplantation mechanism for robotic FUE surgery","authors":"Fulin Jia, Shenghao Yang, Chenxi Han, Junye Li, Xuanru Han, Chao Zhang, Jiaole Wang","doi":"10.1016/j.birob.2023.100128","DOIUrl":"https://doi.org/10.1016/j.birob.2023.100128","url":null,"abstract":"<div><p>Hair transplantation surgery is an effective solution for hair loss problems, among which follicle unit extraction (FUE) surgery is more widely used and favored. At present, most hair transplantation surgeries still rely heavily on manual operation by doctors and very few hair transplantation robots with complex structures have been introduced. This paper proposes a pneumatic hair transplantation mechanism for FUE surgery, equipped with a camera, capable of automatically performing both hair implantation and extraction with airflow. This pneumatic method eliminates the complex needle structure, has the function of temporarily storing the follicles inside the needle, thus facilitating the automation of transferring follicles from extraction to implantation. Then a visual feedback system is proposed to accurately position the follicles during the transplantation. The experimental results show that average distance deviation between the actual and target positions is 0.6128 mm and the average deviation of hair implantation depth is 1.7176 mm, which verify the feasibility of the proposed system.</p></div>","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"3 4","pages":"Article 100128"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667379723000426/pdfft?md5=034fe2b420e2a8a9edac240b27514f0c&pid=1-s2.0-S2667379723000426-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92051119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Positioning system design of closed-loop magnetically driven laser steering manipulator for endoscopic microsurgery 内镜显微手术用闭环磁驱动激光转向机械手定位系统设计

Biomimetic Intelligence and Robotics Pub Date : 2023-10-10 DOI: 10.1016/j.birob.2023.100129

Qi Zhang , Han Xu , Li Zhu , Li Liu

{"title":"Positioning system design of closed-loop magnetically driven laser steering manipulator for endoscopic microsurgery","authors":"Qi Zhang , Han Xu , Li Zhu , Li Liu","doi":"10.1016/j.birob.2023.100129","DOIUrl":"https://doi.org/10.1016/j.birob.2023.100129","url":null,"abstract":"<div><p>This study presents a closed-loop magnetically driven laser steering manipulator positioning system for endoscopic microsurgery. A multimagnetic field strength sensor circuit is embedded in a <span><math><mrow><mn>16</mn><mo>−</mo><mi>mm</mi></mrow></math></span> diameter analog laser steering manipulator. The magnetic field distribution of a cylindrical permanent magnet in three-dimensional space is first modeled using an integral model to overcome the large error induced by the magnetic dipole model when the sensor and permanent magnet are close. The integral in the model is then decomposed using the Gauss–Legendre quadrature to improve the computational efficiency of the formulation. Moreover, five commonly used global search optimization methods are compared. Then, the algorithm with the fastest computational rate among these five algorithms, the tree-seed algorithm, is fused with the Levenberg–Marquardt algorithm, which performs well in local search, to obtain a hybrid optimization algorithm. Finally, it is demonstrated through static and dynamic experiments that the system based on the hybrid algorithm can obtain satisfactory computational errors while maintaining a high computational rate.</p></div>","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"3 4","pages":"Article 100129"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667379723000438/pdfft?md5=c3ffa850361a548289ef48ed036af100&pid=1-s2.0-S2667379723000438-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92149439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive robust control for biped walking under uncertain external forces 不确定外力作用下双足行走的自适应鲁棒控制

Biomimetic Intelligence and Robotics Pub Date : 2023-09-27 DOI: 10.20517/ir.2023.26

Helin Wang, Qijun Chen

引用次数: 0

Funabot-Suit: A bio-inspired and McKibben muscle-actuated suit for natural kinesthetic perception Funabot-Suit:一种仿生和McKibben肌肉驱动的服装，用于自然运动知觉

Biomimetic Intelligence and Robotics Pub Date : 2023-09-22 DOI: 10.1016/j.birob.2023.100127

Yanhong Peng , Yusuke Sakai , Koki Nakagawa , Yuki Funabora , Tadayoshi Aoyama , Kenta Yokoe , Shinji Doki

{"title":"Funabot-Suit: A bio-inspired and McKibben muscle-actuated suit for natural kinesthetic perception","authors":"Yanhong Peng , Yusuke Sakai , Koki Nakagawa , Yuki Funabora , Tadayoshi Aoyama , Kenta Yokoe , Shinji Doki","doi":"10.1016/j.birob.2023.100127","DOIUrl":"https://doi.org/10.1016/j.birob.2023.100127","url":null,"abstract":"<div><p>In recent years, there has been extensive utilization of actuators driven by artificial muscles in wearable devices. However, the muscle distribution configurations of most wearable devices have been specifically designed and are difficult to generalize. Consequently, wearable devices that allow direct installation of actuators onto existing clothing are better suited for a wider range of application scenarios. This letter presents the development and evaluation of Funabot-Suit, a human muscle configuration inspired wearable assist device that employs McKibben artificial muscles to induce natural kinesthetic perception in the wearer’s torso. By integrating thin McKibben muscles into an existing motion capture suit, the Funabot-Suit is capable of generating four fundamental motions: forward and backward bending, and left and right twisting. The suit’s performance was assessed through experiments involving three subjects who wore the suit while standing and seated, with the subjects reporting the direction of their kinesthetic perception. The subjects also rated the perceived ease of kinesthetic perception direction on a five-point scale. Our results demonstrate that the Funabot-Suit successfully induces kinesthetic perceptions for the wearer, with a one hundred percent detection ratio for accurate responses in the command direction across all subjects and positions. We observed variations in the sensitivity of left–right and up-down sensations, which can be attributed to the positioning of artificial muscles and individual differences.</p></div>","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"3 4","pages":"Article 100127"},"PeriodicalIF":0.0,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667379723000414/pdfft?md5=2095b9cbc98b6163dfc3338303d38075&pid=1-s2.0-S2667379723000414-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92103589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Optimization of fracture reduction robot controller based on improved sparrow algorithm 基于改进麻雀算法的骨折复位机器人控制器优化

Biomimetic Intelligence and Robotics Pub Date : 2023-09-19 DOI: 10.1016/j.birob.2023.100120

Baichuan An , Jianwen Chen , Hao Sun , Minghuan Yin , Zicheng Song , Chao Zhuang , Cheng Chang , Minghe Liu

{"title":"Optimization of fracture reduction robot controller based on improved sparrow algorithm","authors":"Baichuan An , Jianwen Chen , Hao Sun , Minghuan Yin , Zicheng Song , Chao Zhuang , Cheng Chang , Minghe Liu","doi":"10.1016/j.birob.2023.100120","DOIUrl":"https://doi.org/10.1016/j.birob.2023.100120","url":null,"abstract":"<div><p>The accuracy of a fracture reduction robot (FRR) is critical for ensuring the safety of surgery. Improving the repositioning accuracy of a FRR, reducing the error, and realizing a safer and more stable folding motion is critical. To achieve this, a sparrow search algorithm (SSA) based on the Levy flight operator was proposed in this study for self-tuning the robot controller parameters. An inverse kinematic analysis of the FRR was also performed. The robot dynamics model was established using Simulink, and the inverse dynamics controller for the fracture reduction mechanism was designed using the computed torque control method. Both simulation and physical experiments were also performed. The actual motion trajectory of the actuator drive rod and its error with a desired trajectory was obtained through simulation. An optimized Levy-sparrow search algorithm (Levy-SSA) crack reduction robot controller demonstrated an overall reduction of two orders of magnitude in the reduction error, with an average error reduction of 98.74% compared with the traditional unoptimized controller. The Levy-SSA increased the convergence of the crack reduction robot control system to the optimal solution, improved the accuracy of the motion trajectory, and exhibited important implications for robot controller optimization.</p></div>","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"3 4","pages":"Article 100120"},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71734442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A distributed multi-vehicle pursuit scheme: generative multi-adversarial reinforcement learning 分布式多车辆追踪方案:生成式多对抗强化学习

Biomimetic Intelligence and Robotics Pub Date : 2023-09-13 DOI: 10.20517/ir.2023.25

Xinhang Li, Yiying Yang, Qinwen Wang, Zheng Yuan, Chen Xu, Lei Li, Lin Zhang

{"title":"A distributed multi-vehicle pursuit scheme: generative multi-adversarial reinforcement learning","authors":"Xinhang Li, Yiying Yang, Qinwen Wang, Zheng Yuan, Chen Xu, Lei Li, Lin Zhang","doi":"10.20517/ir.2023.25","DOIUrl":"https://doi.org/10.20517/ir.2023.25","url":null,"abstract":"Multi-vehicle pursuit (MVP) is one of the most challenging problems for intelligent traffic management systems due to multi-source heterogeneous data and its mission nature. While many reinforcement learning (RL) algorithms have shown promising abilities for MVP in structured grid-pattern roads, their lack of dynamic and effective traffic awareness limits pursuing efficiency. The sparse reward of pursuing tasks still hinders the optimization of these RL algorithms. Therefore, this paper proposes a distributed generative multi-adversarial RL for MVP (DGMARL-MVP) in urban traffic scenes. In DGMARL-MVP, a generative multi-adversarial network is designed to improve the Bellman equation by generating the potential dense reward, thereby properly guiding strategy optimization of distributed multi-agent RL. Moreover, a graph neural network-based intersecting cognition is proposed to extract integrated features of traffic situations and relationships among agents from multi-source heterogeneous data. These integrated and comprehensive traffic features are used to assist RL decision-making and improve pursuing efficiency. Extensive experimental results show that the DGMARL-MVP can reduce the pursuit time by 5.47% compared with proximal policy optimization and improve the pursuing average success rate up to 85.67%. Codes are open-sourced in Github.","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135784311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0