Large language models(LLMs)have undergone significant expansion and have been increasingly integrated across various domains.Notably,in the realm of robot task planning,LLMs harness their advanced reasoning and langua...Large language models(LLMs)have undergone significant expansion and have been increasingly integrated across various domains.Notably,in the realm of robot task planning,LLMs harness their advanced reasoning and language comprehension capabilities to formulate precise and efficient action plans based on natural language instructions.However,for embodied tasks,where robots interact with complex environments,textonly LLMs often face challenges due to a lack of compatibility with robotic visual perception.This study provides a comprehensive overview of the emerging integration of LLMs and multimodal LLMs into various robotic tasks.Additionally,we propose a framework that utilizes multimodal GPT-4V to enhance embodied task planning through the combination of natural language instructions and robot visual perceptions.Our results,based on diverse datasets,indicate that GPT-4V effectively enhances robot performance in embodied tasks.This extensive survey and evaluation of LLMs and multimodal LLMs across a variety of robotic tasks enriches the understanding of LLM-centric embodied intelligence and provides forward-looking insights towards bridging the gap in Human-Robot-Environment interaction.展开更多
The 2025 World Robot Conference,held in Beijing from August 8 to 12,offered a vivid glimpse into the future of the global robotics industry,where breakthroughs in artificial intelligence(AI)are injecting new momentum ...The 2025 World Robot Conference,held in Beijing from August 8 to 12,offered a vivid glimpse into the future of the global robotics industry,where breakthroughs in artificial intelligence(AI)are injecting new momentum into growth.Drawing ove r 1.3 million attendees.展开更多
This study presents a systematic review of applications of artificial intelligence(abbreviated as AI)and blockchain in supply chain provenance traceability and legal forensics cover five sectors:integrated circuits(ab...This study presents a systematic review of applications of artificial intelligence(abbreviated as AI)and blockchain in supply chain provenance traceability and legal forensics cover five sectors:integrated circuits(abbreviated as ICs),pharmaceuticals,electric vehicles(abbreviated as EVs),drones(abbreviated as UAVs),and robotics—in response to rising trade tensions and geopolitical conflicts,which have heightened concerns over product origin fraud and information security.While previous literature often focuses on single-industry contexts or isolated technologies,this reviewcomprehensively surveys these sectors and categorizes 116 peer-reviewed studies by application domain,technical architecture,and functional objective.Special attention is given to traceability control mechanisms,data integrity,and the use of forensic technologies to detect origin fraud.The study further evaluates real-world implementations,including blockchain-enabled drug tracking systems,EV battery raw material traceability,and UAV authentication frameworks,demonstrating the practical value of these technologies.By identifying technological challenges and policy implications,this research provides a comprehensive foundation for future academic inquiry,industrial adoption,and regulatory development aimed at enhancing transparency,resilience,and trust in global supply chains.展开更多
In a late January 2025 program broadcast to a television audience of more than a billion viewers,16 Unitree(Hangzhou,China)H1 humanoid robots joined human performers in a synchronized Yangko dance at the Chinese Sprin...In a late January 2025 program broadcast to a television audience of more than a billion viewers,16 Unitree(Hangzhou,China)H1 humanoid robots joined human performers in a synchronized Yangko dance at the Chinese Spring Festival Gala[1].Each robot featured more than 40 degrees of freedom(DOF)in its limbs,real-time motion planning,and stable gait control using terrainagnostic algorithms.As they danced,the robots mimicked the human dancers in skillfully manipulating handkerchiefs(Fig.1).展开更多
1.Introduction The continuous integration of advanced technologies into medicine has brought profound changes across nearly all specialties.In urology,a field traditionally characterized by its reliance on delicate,pr...1.Introduction The continuous integration of advanced technologies into medicine has brought profound changes across nearly all specialties.In urology,a field traditionally characterized by its reliance on delicate,precision-driven procedures,the impact of innovations such as robotics,artificial intelligence(AI),telepresence,and telesurgery has been transformative.展开更多
Extreme environments are unstructured and change rapidly,making human exploration in unfamiliar areas difficult.Construction robotics can help reduce risks to human safety and property in these environments by integra...Extreme environments are unstructured and change rapidly,making human exploration in unfamiliar areas difficult.Construction robotics can help reduce risks to human safety and property in these environments by integrating digital technology and artificial intelligence.This technology has the potential to significantly improve the quality and efficiency of construction,making it a key area for future research.Extreme environments include hazardous work sites,polluted areas,and harsh natural conditions.Our review of construction robotics in these settings highlights several knowledge gaps.We focused on four main areas:mechanism design,perception,planning,and control.Our analysis reveals challenges in practical applications,such as creating adaptable mechanisms,accurately perceiving changing environments,planning for unstructured sites,and optimizing control models.Future research should explore:biomimetic designs inspired by nature,multimodal data fusion for perception,adaptive planning strategies,and hybrid control models that combine data-driven and mechanism-based approaches.展开更多
This review explores the current state and future prospects of tactile sensing technologies in space robotics,addressing the unique challenges posed by harsh space environments such as extreme temperatures,radiation,m...This review explores the current state and future prospects of tactile sensing technologies in space robotics,addressing the unique challenges posed by harsh space environments such as extreme temperatures,radiation,microgravity,and vacuum conditions,which necessitate specialized sensor designs.We provide a detailed analysis of four primary types of tactile sensors:resistive,capacitive,piezoelectric,and optical,evaluating their operating principles,advantages,limitations,and specific applications in space exploration.Recent advancements in materials science,including the development of radiation-hardened components and flexible sensor materials,are discussed alongside innovations in sensor design and integration techniques that enhance performance and durability under space conditions.Through case studies of various space robotic systems,such as Mars rovers,robotic arms like Canadarm,humanoid robots like Robonaut,and specialized robots like Astrobee and LEMUR 3,this review highlights the crucial role of tactile sensing in enabling precise manipulation,environmental interaction,and autonomous operations in space.Moreover,it synthesizes current research and applications to underscore the transformative impact of tactile sensing technologies on space robotics and highlights their pivotal role in expanding human presence and scientific understanding in space,offering strategic insights and recommendations to guide future research and development in this critical field.展开更多
The embodied artificial intelligence(EAI)is driving a significant transformation in robotics,enhancing their autonomy,efficiency and evolution ability.In this rapidly evolving technological landscape,robots need numer...The embodied artificial intelligence(EAI)is driving a significant transformation in robotics,enhancing their autonomy,efficiency and evolution ability.In this rapidly evolving technological landscape,robots need numerous sensors to realize high levels of perception,precision,safety,adaptability,and intelligence.Triboelectric and piezoelectric sensors address these needs by providing high sensitivity,flexibility,and the capability of self-powered sensing,leveraging the revolutionary nature of nanogenerators to convert mechanical energy into electrical energy on basis of Maxwell’s displacement current.These sensors surpass externally powered passive sensors by offering continuous operation,reduced maintenance,and the capability to function in remote or harsh environments.The integration of EAI with advanced nanogenerators sensors could position robotics to perform autonomously,efficiently,and safely,paving the way for innovative applications in various domains such as industrial automation,environmental monitoring,healthcare,and smart homes.In this paper,the fundamental theories,design,manufacturing,and applications of nanogenerators are comprehensively reviewed as afoundation of the advanced sensors for intelligent robotics in the new era,with three major application fields:sensing(including human–robot interaction,exteroceptive sensing and proprioceptive sensing),computing and actuating.Perspectives are addressed for nanogenerators systems in future development.展开更多
With the acceleration of the global aging process and the increase of cardiovascular ancerebrovascular diseases,more and more patients are paralyzed due to accidents,so theexoskeleton robot began to appear in people&#...With the acceleration of the global aging process and the increase of cardiovascular ancerebrovascular diseases,more and more patients are paralyzed due to accidents,so theexoskeleton robot began to appear in people's sight,and the lower limb exoskeleton robot withrehabilitation training is also favored by more and more people.In this paper,the structural designand analysis of the lower limb exoskeleton robot are carried out in view of the patients'expectation ofnormal walking.First,gait analysis and structural design of lower limb exoskeleton robot.Based onthe analysis of the walking gait of normal people,the freedom of the three key joints of the lower limbexoskeleton robot hip joint,knee joint and ankle joint is determined.at the same time,according tothe structuralcharacteristics of each joint,the three key joints are modeled respectively,and theoverall model assembly of the lower limb exoskeleton robot is completed.Secondly,the kinematicsanalysis of the lower limb exoskeleton robot was carried out to obtain the relationship between thelinear displacement,linear speed and acceleration of each joint,so as to ensure the coordination ofthe model with the human lower limb movement.Thirdly,the static analysis of typical gait of hipjoint,knee joint and ankle joint is carried out to verify the safety of the design model under thepremise of ensuring the structural strength requirements.Finally,the parts of the model were 3Dprinted,and the rationality of the design was further verified in the process of assembling the model.展开更多
Robots are key to expanding the scope of space applications.The end-to-end training for robot vision-based detection and precision operations is challenging owing to constraints such as extreme environments and high c...Robots are key to expanding the scope of space applications.The end-to-end training for robot vision-based detection and precision operations is challenging owing to constraints such as extreme environments and high computational overhead.This study proposes a lightweight integrated framework for grasp detection and imitation learning,named GD-IL;it comprises a grasp detection algorithm based on manipulability and Gaussian mixture model(manipulability-GMM),and a grasp trajectory generation algorithm based on a two-stage robot imitation learning algorithm(TS-RIL).In the manipulability-GMM algorithm,we apply GMM clustering and ellipse regression to the object point cloud,propose two judgment criteria to generate multiple candidate grasp bounding boxes for the robot,and use manipulability as a metric for selecting the optimal grasp bounding box.The stages of the TS-RIL algorithm are grasp trajectory learning and robot pose optimization.In the first stage,the robot grasp trajectory is characterized using a second-order dynamic movement primitive model and Gaussian mixture regression(GMM).By adjusting the function form of the forcing term,the robot closely approximates the target-grasping trajectory.In the second stage,a robot pose optimization model is built based on the derived pose error formula and manipulability metric.This model allows the robot to adjust its configuration in real time while grasping,thereby effectively avoiding singularities.Finally,an algorithm verification platform is developed based on a Robot Operating System and a series of comparative experiments are conducted in real-world scenarios.The experimental results demonstrate that GD-IL significantly improves the effectiveness and robustness of grasp detection and trajectory imitation learning,outperforming existing state-of-the-art methods in execution efficiency,manipulability,and success rate.展开更多
Single-cell biomechanics and electrophysiology measuring tools have transformed biological research over the last few decades,which enabling a comprehensive and nuanced understanding of cellular behavior and function....Single-cell biomechanics and electrophysiology measuring tools have transformed biological research over the last few decades,which enabling a comprehensive and nuanced understanding of cellular behavior and function.Despite their high-quality information content,these single-cell measuring techniques suffer from laborious manual processing by highly skilled workers and extremely low throughput(tens of cells per day).Recently,numerous researchers have automated the measurement of cell mechanical and electrical signals through robotic localization and control processes.While these efforts have demonstrated promising progress,critical challenges persist,including human dependency,learning complexity,in-situ measurement,and multidimensional signal acquisition.To identify key limitations and highlight emerging opportunities for innovation,in this review,we comprehensively summarize the key steps of robotic technologies in single-cell biomechanics and electrophysiology.We also discussed the prospects and challenges of robotics and automation in biological research.By bridging gaps between engineering,biology,and data science,this work aims to stimulate interdisciplinary research and accelerate the translation of robotic single-cell technologies into practical applications in the life sciences and medical fields.展开更多
基金supported by National Natural Science Foundation of China(62376219 and 62006194)Foundational Research Project in Specialized Discipline(Grant No.G2024WD0146)Faculty Construction Project(Grant No.24GH0201148).
文摘Large language models(LLMs)have undergone significant expansion and have been increasingly integrated across various domains.Notably,in the realm of robot task planning,LLMs harness their advanced reasoning and language comprehension capabilities to formulate precise and efficient action plans based on natural language instructions.However,for embodied tasks,where robots interact with complex environments,textonly LLMs often face challenges due to a lack of compatibility with robotic visual perception.This study provides a comprehensive overview of the emerging integration of LLMs and multimodal LLMs into various robotic tasks.Additionally,we propose a framework that utilizes multimodal GPT-4V to enhance embodied task planning through the combination of natural language instructions and robot visual perceptions.Our results,based on diverse datasets,indicate that GPT-4V effectively enhances robot performance in embodied tasks.This extensive survey and evaluation of LLMs and multimodal LLMs across a variety of robotic tasks enriches the understanding of LLM-centric embodied intelligence and provides forward-looking insights towards bridging the gap in Human-Robot-Environment interaction.
文摘The 2025 World Robot Conference,held in Beijing from August 8 to 12,offered a vivid glimpse into the future of the global robotics industry,where breakthroughs in artificial intelligence(AI)are injecting new momentum into growth.Drawing ove r 1.3 million attendees.
文摘This study presents a systematic review of applications of artificial intelligence(abbreviated as AI)and blockchain in supply chain provenance traceability and legal forensics cover five sectors:integrated circuits(abbreviated as ICs),pharmaceuticals,electric vehicles(abbreviated as EVs),drones(abbreviated as UAVs),and robotics—in response to rising trade tensions and geopolitical conflicts,which have heightened concerns over product origin fraud and information security.While previous literature often focuses on single-industry contexts or isolated technologies,this reviewcomprehensively surveys these sectors and categorizes 116 peer-reviewed studies by application domain,technical architecture,and functional objective.Special attention is given to traceability control mechanisms,data integrity,and the use of forensic technologies to detect origin fraud.The study further evaluates real-world implementations,including blockchain-enabled drug tracking systems,EV battery raw material traceability,and UAV authentication frameworks,demonstrating the practical value of these technologies.By identifying technological challenges and policy implications,this research provides a comprehensive foundation for future academic inquiry,industrial adoption,and regulatory development aimed at enhancing transparency,resilience,and trust in global supply chains.
文摘In a late January 2025 program broadcast to a television audience of more than a billion viewers,16 Unitree(Hangzhou,China)H1 humanoid robots joined human performers in a synchronized Yangko dance at the Chinese Spring Festival Gala[1].Each robot featured more than 40 degrees of freedom(DOF)in its limbs,real-time motion planning,and stable gait control using terrainagnostic algorithms.As they danced,the robots mimicked the human dancers in skillfully manipulating handkerchiefs(Fig.1).
文摘1.Introduction The continuous integration of advanced technologies into medicine has brought profound changes across nearly all specialties.In urology,a field traditionally characterized by its reliance on delicate,precision-driven procedures,the impact of innovations such as robotics,artificial intelligence(AI),telepresence,and telesurgery has been transformative.
基金supported in the Strategic Research and Consulting Project of the Chinese Academy of Engineering(2023-XZ-90 and 2023-JB-09-10)the National Key Research and Development Program of China(2021YFF0500301 and 2023YFB3711300)+1 种基金the National Natural Science Foundation of China(72171092 and 71821001)the Natural Science Fund for Distinguished Young Scholars of Hubei Province(2021CFA091).
文摘Extreme environments are unstructured and change rapidly,making human exploration in unfamiliar areas difficult.Construction robotics can help reduce risks to human safety and property in these environments by integrating digital technology and artificial intelligence.This technology has the potential to significantly improve the quality and efficiency of construction,making it a key area for future research.Extreme environments include hazardous work sites,polluted areas,and harsh natural conditions.Our review of construction robotics in these settings highlights several knowledge gaps.We focused on four main areas:mechanism design,perception,planning,and control.Our analysis reveals challenges in practical applications,such as creating adaptable mechanisms,accurately perceiving changing environments,planning for unstructured sites,and optimizing control models.Future research should explore:biomimetic designs inspired by nature,multimodal data fusion for perception,adaptive planning strategies,and hybrid control models that combine data-driven and mechanism-based approaches.
基金supported by FAST(19FAYORA14)of the Canadian Space Agency,Discovery Grant(RGPIN2024-06290)supported by CREATE grant(555425-2021)&Discovery grant(RGPIN-2024-06290)of the Natural Sciences and Engineering Research Council of Canada.
文摘This review explores the current state and future prospects of tactile sensing technologies in space robotics,addressing the unique challenges posed by harsh space environments such as extreme temperatures,radiation,microgravity,and vacuum conditions,which necessitate specialized sensor designs.We provide a detailed analysis of four primary types of tactile sensors:resistive,capacitive,piezoelectric,and optical,evaluating their operating principles,advantages,limitations,and specific applications in space exploration.Recent advancements in materials science,including the development of radiation-hardened components and flexible sensor materials,are discussed alongside innovations in sensor design and integration techniques that enhance performance and durability under space conditions.Through case studies of various space robotic systems,such as Mars rovers,robotic arms like Canadarm,humanoid robots like Robonaut,and specialized robots like Astrobee and LEMUR 3,this review highlights the crucial role of tactile sensing in enabling precise manipulation,environmental interaction,and autonomous operations in space.Moreover,it synthesizes current research and applications to underscore the transformative impact of tactile sensing technologies on space robotics and highlights their pivotal role in expanding human presence and scientific understanding in space,offering strategic insights and recommendations to guide future research and development in this critical field.
基金supported by the National Natural Science Foundation of China(Grants Nos.62104125and 62311530102)Shenzhen Science and Technology Program(Grant Nos.JCYJ20220530143013030 and JCYJ20240813111910014)+1 种基金Guangdong Innovative and Entrepreneurial Research Team Program(Grant No.2021ZT09L197)Tsinghua Shenzhen International Graduate School-Shenzhen Pengrui Young Faculty Program of Shenzhen Pengrui Foundation(Grant No.SZPR2023005)。
文摘The embodied artificial intelligence(EAI)is driving a significant transformation in robotics,enhancing their autonomy,efficiency and evolution ability.In this rapidly evolving technological landscape,robots need numerous sensors to realize high levels of perception,precision,safety,adaptability,and intelligence.Triboelectric and piezoelectric sensors address these needs by providing high sensitivity,flexibility,and the capability of self-powered sensing,leveraging the revolutionary nature of nanogenerators to convert mechanical energy into electrical energy on basis of Maxwell’s displacement current.These sensors surpass externally powered passive sensors by offering continuous operation,reduced maintenance,and the capability to function in remote or harsh environments.The integration of EAI with advanced nanogenerators sensors could position robotics to perform autonomously,efficiently,and safely,paving the way for innovative applications in various domains such as industrial automation,environmental monitoring,healthcare,and smart homes.In this paper,the fundamental theories,design,manufacturing,and applications of nanogenerators are comprehensively reviewed as afoundation of the advanced sensors for intelligent robotics in the new era,with three major application fields:sensing(including human–robot interaction,exteroceptive sensing and proprioceptive sensing),computing and actuating.Perspectives are addressed for nanogenerators systems in future development.
基金College Student Innovation andEntrepreneurship Project(Grant No.:S202414435026)ingkou Institute of Technology campus level research project——Development of food additive supercritical extraction equipment and fluid transmission systemresearch(Grant No.HX202427).
文摘With the acceleration of the global aging process and the increase of cardiovascular ancerebrovascular diseases,more and more patients are paralyzed due to accidents,so theexoskeleton robot began to appear in people's sight,and the lower limb exoskeleton robot withrehabilitation training is also favored by more and more people.In this paper,the structural designand analysis of the lower limb exoskeleton robot are carried out in view of the patients'expectation ofnormal walking.First,gait analysis and structural design of lower limb exoskeleton robot.Based onthe analysis of the walking gait of normal people,the freedom of the three key joints of the lower limbexoskeleton robot hip joint,knee joint and ankle joint is determined.at the same time,according tothe structuralcharacteristics of each joint,the three key joints are modeled respectively,and theoverall model assembly of the lower limb exoskeleton robot is completed.Secondly,the kinematicsanalysis of the lower limb exoskeleton robot was carried out to obtain the relationship between thelinear displacement,linear speed and acceleration of each joint,so as to ensure the coordination ofthe model with the human lower limb movement.Thirdly,the static analysis of typical gait of hipjoint,knee joint and ankle joint is carried out to verify the safety of the design model under thepremise of ensuring the structural strength requirements.Finally,the parts of the model were 3Dprinted,and the rationality of the design was further verified in the process of assembling the model.
基金Supported by National Natural Science Foundation of China(Grant No.52475280)Shaanxi Provincial Natural Science Basic Research Program(Grant No.2025SYSSYSZD-105).
文摘Robots are key to expanding the scope of space applications.The end-to-end training for robot vision-based detection and precision operations is challenging owing to constraints such as extreme environments and high computational overhead.This study proposes a lightweight integrated framework for grasp detection and imitation learning,named GD-IL;it comprises a grasp detection algorithm based on manipulability and Gaussian mixture model(manipulability-GMM),and a grasp trajectory generation algorithm based on a two-stage robot imitation learning algorithm(TS-RIL).In the manipulability-GMM algorithm,we apply GMM clustering and ellipse regression to the object point cloud,propose two judgment criteria to generate multiple candidate grasp bounding boxes for the robot,and use manipulability as a metric for selecting the optimal grasp bounding box.The stages of the TS-RIL algorithm are grasp trajectory learning and robot pose optimization.In the first stage,the robot grasp trajectory is characterized using a second-order dynamic movement primitive model and Gaussian mixture regression(GMM).By adjusting the function form of the forcing term,the robot closely approximates the target-grasping trajectory.In the second stage,a robot pose optimization model is built based on the derived pose error formula and manipulability metric.This model allows the robot to adjust its configuration in real time while grasping,thereby effectively avoiding singularities.Finally,an algorithm verification platform is developed based on a Robot Operating System and a series of comparative experiments are conducted in real-world scenarios.The experimental results demonstrate that GD-IL significantly improves the effectiveness and robustness of grasp detection and trajectory imitation learning,outperforming existing state-of-the-art methods in execution efficiency,manipulability,and success rate.
基金the National Natural Science Foundation of China[62525301,62127811,62433019]the New Cornerstone Science Foundation through the XPLORER PRIZEthe financial support by the China Postdoctoral Science Foundation[GZB20240797].
文摘Single-cell biomechanics and electrophysiology measuring tools have transformed biological research over the last few decades,which enabling a comprehensive and nuanced understanding of cellular behavior and function.Despite their high-quality information content,these single-cell measuring techniques suffer from laborious manual processing by highly skilled workers and extremely low throughput(tens of cells per day).Recently,numerous researchers have automated the measurement of cell mechanical and electrical signals through robotic localization and control processes.While these efforts have demonstrated promising progress,critical challenges persist,including human dependency,learning complexity,in-situ measurement,and multidimensional signal acquisition.To identify key limitations and highlight emerging opportunities for innovation,in this review,we comprehensively summarize the key steps of robotic technologies in single-cell biomechanics and electrophysiology.We also discussed the prospects and challenges of robotics and automation in biological research.By bridging gaps between engineering,biology,and data science,this work aims to stimulate interdisciplinary research and accelerate the translation of robotic single-cell technologies into practical applications in the life sciences and medical fields.
