期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到59篇文章
< 1 2 3 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
The Next Chapter of Human‐Like Tactile Perception:Neural Decoding to Embodied Intelligence 认领 引用
1
作者 Longwei Li Hao Sun +3 位作者 Jing Wang Zi Hao Guo Xiong Pu Fuchun Sun 《SmartSys》 2026年第2期9-19,共11页
The field of tactile perception is transitioning from phenomenological analysis to integrated application and creation.To develop intelligent and embodied tactile capabilities,it is necessary to move beyond the tradit... The field of tactile perception is transitioning from phenomenological analysis to integrated application and creation.To develop intelligent and embodied tactile capabilities,it is necessary to move beyond the traditional view of touch as a passive input channel and instead understand it as an active closed‐loop computational process.This requires the convergence of multiple disciplines,including materials science,neuroscience,robotics,and computer science,to establish a unified framework centered on active perception,predictive processing,and sensorimotor integration.This framework will guide the co‐design of intelligent devices,brain‐like algorithms,and scalable systems.Such advancements will drive the transformation of human–digital interaction,physical environment manipulation,and interpersonal connectivity,thereby enabling more natural and efficient human–machine collaboration. 展开更多
关键词 cross‐modal algorithms embodied intelligence neural decoding tactile perception tactile sensors
暂未订购 下载PDF
Application Prospects of Robots in the Field of Clinical Nursing Under the Background of Embodied Intelligence 认领 引用
2
作者 Hui Qin 《Journal of Clinical and Nursing Research》 2026年第4期353-359,共7页
With the acceleration of the aging population and the increasingly prominent contradiction between the supply and demand of medical resources,the field of clinical nursing is also facing new challenges and opportuniti... With the acceleration of the aging population and the increasingly prominent contradiction between the supply and demand of medical resources,the field of clinical nursing is also facing new challenges and opportunities.Embodied Intelligence(EI)is a cutting-edge branch of artificial intelligence,emphasizing that intelligent agents achieve the unity of cognition and action through dynamic interaction between physical carriers and the environment,which has injected vivid vitality into the development of clinical nursing robots.Based on this,this paper will briefly analyze the core connotation and technical characteristics of embodied intelligence,as well as the application scenarios of nursing robots in the field of clinical nursing,and look forward to the application prospects of nursing robots in the field of clinical nursing under the background of embodied intelligence,aiming to promote the deep integration of embodied intelligence technology and the field of clinical nursing. 展开更多
关键词 Embodied intelligence Robots Clinical nursing
暂未订购 下载PDF
Gewu Playground:An open-source robot simulation platform for embodied intelligence research 认领 引用
3
作者 Linqi YE Boyang XING +2 位作者 Bin LIANG Lei JIANG Yan PENG 《Science China(Technological Sciences)》 SCIE EI CAS CSCD 2026年第6期418-420,共3页
Simulation platforms are pivotal to robotics research and have greatly advanced the development of the robotics field.Traditional robotic simulation tools such as Webots[1],Gazebo[2],and V-REP(now Coppelia Sim)[3]have... Simulation platforms are pivotal to robotics research and have greatly advanced the development of the robotics field.Traditional robotic simulation tools such as Webots[1],Gazebo[2],and V-REP(now Coppelia Sim)[3]have notably contributed to the field by supporting kinematic and dynamic model-based research.However,as artificial intelligence and robotics converge ever more closely,robotics research has entered the era of embodied intelligence,rendering traditional robotic simulation platforms inadequate for current research needs. 展开更多
关键词 embodied intelligencerendering research platforms simulation simulation tools robotics embodied intelligence artificial intelligence simulation platforms
暂未订购 下载PDF
EIoT:Embodied Intelligence of Things 认领 引用
4
作者 Yunhao Liu Xu Wang +4 位作者 Yunhuai Liu Kebin Liu Shuai Tong Jinliang Yuan Li Liu 《Tsinghua Science and Technology》 SCIE EI CAS CSCD 2026年第1期1-15,共15页
The integration of embodied intelligence into physical environments marks a new frontier in the evolution of intelligent systems.While the Internet of Things(IoT)connects devices and Artificial Intelligence of Things(... The integration of embodied intelligence into physical environments marks a new frontier in the evolution of intelligent systems.While the Internet of Things(IoT)connects devices and Artificial Intelligence of Things(AIoT)embeds intelligence into them,we argue that a further conceptual leap is required—one that enables the composition of intelligence itself through real-world embodiment,interaction,and evolution.We introduce the paradigm of Embodied Intelligence of Things(EIoT)as a foundational framework for distributed,physically grounded intelligent systems.EIoT systems are structured across three essential dimensions:Enacted,where devices are transformed into embodied agents;Engaged,where agents interact opportunistically based on physical and contextual constraints;and Evolutionary,where intelligence adapts and self-organizes through continuous experience.We further outline a developmental trajectory for EIoT based on the openness of perception and decision spaces,providing a conceptual map from tightly constrained agents to fully autonomous and adaptive systems.This work aims to establish EIoT as a core architectural and theoretical direction for future embodied intelligent systems. 展开更多
关键词 embodied intelligence of things compositional intelligence multi-agent coordination edge intelligence physical-digital interaction
暂未订购 下载PDF
Insect-scale robots with embodied intelligence:Challenges and future perspectives 认领 引用
5
作者 Yexi Zhou Dongkai Wang +2 位作者 Yanting Gong Iek Man Lei Junwen Zhong 《eScience》 SCIE CSCD 2026年第4期1-10,共10页
Inspired by the agility,adaptability,and efficiency of insects,insect-scale robots are emerging as promising platforms for applications in environmental monitoring,search and rescue,precision agriculture,and beyond.Ho... Inspired by the agility,adaptability,and efficiency of insects,insect-scale robots are emerging as promising platforms for applications in environmental monitoring,search and rescue,precision agriculture,and beyond.However,a central challenge lies in achieving advanced embodied intelligence,where smart,adaptive behaviors arise from the seamless integration of a robot’s physical form,actuation,sensing,and control under severe size and power constraints.Recent breakthroughs in soft materials,bio-inspired actuation,energy harvesting,and lightweight AI have enabled significant progress,enhancing mobility and foundational autonomy.Furthermore,collective intelligence,achieved through robot swarms that mimic insect societies,offers a powerful extension of embodied intelligence for distributed sensing and cooperative task execution.This perspective paper examines the current state of insect-scale robots,identifies persistent challenges in miniaturization and autonomy,and proposes a roadmap for future advancement,focusing on hybrid material systems,energy-efficient cognition,and scalable swarm intelligence to transition from laboratory prototypes to practical,intelligent systems. 展开更多
关键词 Micro robotics Embodied intelligence Actuating Sensing AI algorithm Physical intelligence
Embodied-Intelligence Power Industrial Control Systems:Architecture Design,Key Scientific Problems,and Research Recommendations 认领 引用
6
作者 Tingjun Zhang Dong Yue 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第2期239-242,共4页
THE power industrial control system(power ICS)is thecore infrastructure that ensures the safe,stable,and efficient operation of power systems.Its architecture typi-cally adopts a hierarchical and partitioned end-edge-... THE power industrial control system(power ICS)is thecore infrastructure that ensures the safe,stable,and efficient operation of power systems.Its architecture typi-cally adopts a hierarchical and partitioned end-edge-cloud collaborative design.However,the large-scale integration ofdistributed renewable energy resources,coupled with the extensivedeployment of sensing and communication devices,has resulted inthe new-type power system characterized by dynamic complexityand high uncertainty[1]-[4]. 展开更多
关键词 power system embodied intelligence power industrial control system power architecture design key scientific problems power industrial control systems sensing communication deviceshas renewable energy resourcescoupled
暂未订购 下载PDF
ON THE RECONSTRUCTION OF TORT LIABILITY RULES FOR EMBODIED INTELLIGENCE INFRINGEMENTS 认领 引用
7
作者 Liu Hui 《China Legal Science》 2026年第3期3-32,共30页
Against the backdrop of the booming market of embodied intelligence,the inherent infringement risks warrant heightened vigilance.Characterized by the concealment and unpredictability of its actions,traditional tort li... Against the backdrop of the booming market of embodied intelligence,the inherent infringement risks warrant heightened vigilance.Characterized by the concealment and unpredictability of its actions,traditional tort liability rules face multiple challenges,including establishing tortious facts,selecting imputation principles for liable entities,determining causation,and identifying defenses.In the era of human-machine symbiosis,tort law should further undergo a transformation in its underlying logic across three dimensions:emphasizing distributive justice,establishing the independence of the preventive function,and integrating harmony as an objective.Consequently,the reconstruction of tort liability rules should involve:appropriately lowering the standard of proof for tortious facts;applying existing product liability rules to producers and sellers while refining the standards for identifying'defects',applying a presumption of fault principle to users and clarifying their duty of care;addressing the difficulty in establishing causation through a joint liability approach;and strictly determining victim fault and intent while moderately weakening the application of the victim consent rule. 展开更多
关键词 embodied intelligence establishing tortious factsselecting imputation principles infringement risks traditional tort liability rules embodied intelligencethe reconstruction identifying defensesin tort liability rules
暂未订购 下载PDF
Mechanics-guided design of flexible pressure sensors:bridging multiscale electromechanical mechanism to tactile-enabled embodied intelligence 认领 引用
8
作者 Wenxuan Ding Weihe Chen +6 位作者 Guanyu Chen Yonglin Chen Xiaodong Xia Wenbin Kang Zhuangjian Liu Yan Li Weidong Yang 《International Journal of Smart and Nano Materials》 SCIE EI 2026年第1期450-490,共41页
As artificial intelligence(AI)transitions from the virtual to the physical realm,embodied intelligence equips agents with real-time interaction and feedback capabilities.Within the closed-loop‘perception-decision-exe... As artificial intelligence(AI)transitions from the virtual to the physical realm,embodied intelligence equips agents with real-time interaction and feedback capabilities.Within the closed-loop‘perception-decision-execution’paradigm,environmental pressure feedback governs action decisions,while concurrent actions dynamically reshape perception.Consequently,adaptive and precise perception serves as the cornerstone of embodied intelligence.Flexible pressure sensors are pivotal in enabling tactile perceptions,translating subtle mechanical stimuli into measurable electrical signals via intrinsic electromechanical coupling mechanisms.This functionality allows intelligent systems to discern physical properties such as texture,shape and composition.This review systematically summarizes the mechanics-guided design of flexible pressure sensors,bridging multiscale electromechanical coupling behaviors with diverse tactile perception applications.It begins by elucidating the fundamental transduction mechanisms,including capacitive,piezoresistive,piezoelectric,and triboelectric,alongside theoretical advances in regulating electromechanical behaviors.Subsequently,it discusses fabrication techniques,emphasizing how microstructural design influences sensitivity,stability,and dynamic responses.Finally,it addresses the integration of high-performance pressure sensors with AI for tactile-enabled embodied intelligence,advanced perception and adaptive control.Looking ahead,interdisciplinary collaboration across mechanics,material science,and computer science is essential to unravel persistent challenges in electromechanical coupling and propel the development of multifunctional tactile sensory systems. 展开更多
关键词 Embodied intelligence multiscale electromechanical mechanism tactile perception flexible pressure sensor microstructure generative AI electronic skin
Multimodal information-fused embodied intelligence toward autonomous robotic microsurgery 认领 引用
9
作者 Yawen Deng Zhen Li +3 位作者 Qiang Ye Yupeng Zhai Zhangguo Yu Gui-Bin Bian 《The Innovation》 EI 2026年第5期13-14,共2页
Autonomous surgery offers potential to enhance consistency,improve patient safety,reduce differences in surgeon performance,shorten training periods,and decrease dependency on human resources.Autonomy levels for medic... Autonomous surgery offers potential to enhance consistency,improve patient safety,reduce differences in surgeon performance,shorten training periods,and decrease dependency on human resources.Autonomy levels for medical robotics are no autonomy,robot assistance,task autonomy,conditional autonomy,high autonomy,and full autonomy.1 Currently,task and conditional autonomy have been achieved in laparoscopic and intracavitary surgery. 展开更多
关键词 embodied intelligence conditional autonomy medical robotics laparoscopic intracavitary surgery autonomous surgery differences surgeon performanceshorten multimodal information enhance consistencyimprove
Embodied Interactive Intelligence Towards Autonomous Driving 认领 引用
10
作者 Nan Ma Jia Pan +7 位作者 Yongjin Liu Yajue Yang Yiheng Han Jiacheng Guo Zhixuan Wu Zecheng Yang Zhiwei Yang Deyi Li 《Engineering》 SCIE EI CSCD 2026年第4期337-351,共15页
Autonomous driving depends on successful interactions among humans,vehicles,and roads.However,people often lack an understanding of autonomous vehicle(AV)behaviours and decisions.Moreover,AVs have difficulty aligning ... Autonomous driving depends on successful interactions among humans,vehicles,and roads.However,people often lack an understanding of autonomous vehicle(AV)behaviours and decisions.Moreover,AVs have difficulty aligning with human intentions in their interactions.To overcome the obstacles associated with the absence of interactive intelligence,especially in complex and uncertain environments,we introduce the concept of embodied interactive intelligence towards autonomous driving(EIIAD),which establishes representation and learning methods aligned with the physical world,enhancing human-machine integration.Building on this concept,we propose an end-to-end unified constrained vehicle environment interaction(UniCVE)model,which involves the construction of an end-to-end perception-cognition-behaviour closed-loop feedback paradigm and continuous learning through accumulated split driving scenarios.This model realizes interaction cognition through networks designed for pedestrians and vehicles,and it unifies the cognition as a value network of AVs to generate socially compatible behaviours.The UniCVE model is implemented on Dongfeng autonomous buses,which have successfully travelled 22 thousand kilometres and completed 45 thousand navigation tasks in Xiong’an New Area,China,demonstrating its general applicability in various driving scenarios.In addition,we highlight the high-level interactive intelligence of the UniCVE model in selected simulated complex interaction scenarios,demonstrating that it makes AVs more intelligent,more reliable,and more attuned to human relationships.Furthermore,the UniCVE model’s capacity for self-learning and self-growth allows it to infinitely approximate true intelligence,even with limited experience. 展开更多
关键词 Embodied interactive intelligence Autonomous driving Cognition behaviour Continuous learning Hypergraph learning
暂未订购 下载PDF
Call for Papers Special Issue on Security and Safety in Embodied Intelligence 认领 引用
11
《Security and Safety》 CSCD 2026年第1期121-121,共1页
Background As a key bridge connecting artifcial intelligence and the physical world, embodied intelligence, by virtue of the real-time interaction, dynamic learning, and autonomous decision-making capabilities of inte... Background As a key bridge connecting artifcial intelligence and the physical world, embodied intelligence, by virtue of the real-time interaction, dynamic learning, and autonomous decision-making capabilities of intelligent agents with the environment, is rapidly penetrating into various scenarios such as industrial production, service industries, and family life. The application of embodied intelligence technology has greatly improved production efficiency and life convenience. 展开更多
关键词 intelligent agents industrial production Artificial Intelligence Safety artifcial intelligence dynamic learning embodied intelligence Security
Beyond the Cloud:The Rise Of Embodied Intelligence 认领 引用
12
作者 Jay Ian Birbeck 《Beijing Review》 2026年第2期24-25,共2页
The Chinese equivalent of Cambridge Dictionary’s Word of the Year was an-nounced in December 2025.Near the top of language magazine Yaowen Jiaozi's list of defining phrases was"embodied intelligence"(ju... The Chinese equivalent of Cambridge Dictionary’s Word of the Year was an-nounced in December 2025.Near the top of language magazine Yaowen Jiaozi's list of defining phrases was"embodied intelligence"(jushen hineng in Chinese). 展开更多
关键词 intelligence jushen hineng Embodied Intelligence
暂未订购 下载PDF
Editorial for Special Issue on Embodied Intelligence 认领 引用 被引量：1
13
作者 Wei He Chenguang Yang +3 位作者 Long Cheng Zhichuang Wang Jin Wu Luka Peternel 《Machine Intelligence Research》 EI CSCD 2025年第4期585-587,共3页
Embodied intelligence emphasizes the synergy between body,mind,and environment,offering a powerful framework for building more adaptive and interactive intelligent systems.Over the past decade,rapid advancements in ar... Embodied intelligence emphasizes the synergy between body,mind,and environment,offering a powerful framework for building more adaptive and interactive intelligent systems.Over the past decade,rapid advancements in artificial intelligence have driven remarkable achievements in perception,planning,and control tasks,particularly through the rise of deep learning.However,embodied intelligence–the integration of AI with a physical body interacting in real environments–remains a relatively underexplored frontier.Unlike disembodied systems that rely solely on static datasets,embodied agents learn through real-time interaction with their surroundings,leveraging perception-action loops to adaptively understand and manipulate the world.Inspired by human cognition,embodied intelligence emphasizes learning by doing,thereby offering the potential to generalize knowledge across tasks,environments,and sensorimotor experiences. 展开更多
关键词 deep learninghoweverembodied intelligence perception planning embodied intelligence interactive intelligent systemsover artificial intelligence integration ai physical body
Considerations and Normative Construction of Patentability for Technical Solutions Generated by Embodied Artificial Intelligence 认领 引用 被引量：1
14
作者 Li Xiang 《科技与法律（中英文）》 CSSCI 2025年第5期137-148,共12页
Embodied intelligence represents a new paradigm for the cross-integration development of artificial intelli⁃gence.By endowing AI with a"physical body",it enables interaction with the real world,allowing AI t... Embodied intelligence represents a new paradigm for the cross-integration development of artificial intelli⁃gence.By endowing AI with a"physical body",it enables interaction with the real world,allowing AI to move beyond digital environments into the physical realm and demonstrate intelligence that simulates or even surpasses human capa⁃bilities.Although embodied artificial intelligence demonstrates substantial potential in the realm of invention and cre⁃ation,there remain challenges in obtaining patent authorization for its generated technical solutions,specifically con⁃cerning subject,object,and market aspects.To address these issues,the feasibility of the subject should be demon⁃strated from the perspective of embodied cognition theory,while the object should be justified from a techno-centric standpoint.Subsequently,a regulatory framework for the patentability of technical solutions generated by embodied in⁃telligence should be proposed.First,a more inclusive subject framework should be established,recognizing embodied artificial intelligence as an inventor alongside humans,thereby affirming a coexistent"inventor"identity.Second,pat⁃ent rights should be assigned to developers of embodied artificial intelligence,referencing the rights distribution para⁃digm under employment relationships.Third,the criteria for patent eligibility and the"three-aspect"examination stan⁃dards should be refined.Finally,mechanisms for optimizing the implementation of rights and risk prevention should be developed. 展开更多
关键词 embodied artificial intelligence Patent Law techno-centrism emergence inventing entity
暂未订购 下载PDF
Call for Papers Special Issue on Security and Safety in Embodied Intelligence 认领 引用
15
《Security and Safety》 CSCD 2025年第3期86-86,共1页
Background As a key bridge connecting artificial intelligence and the physical world, embodied intelligence, by virtue of the real-time interaction, dynamic learning, and autonomous decision-making capabilities of int... Background As a key bridge connecting artificial intelligence and the physical world, embodied intelligence, by virtue of the real-time interaction, dynamic learning, and autonomous decision-making capabilities of intelligent agents with the environment, is rapidly penetrating into various scenarios such as industrial production, service industries, and family life. The application of embodied intelligence technology has greatly improved production efficiency and life convenience. However, as the coupling between embodied intelligence systems and the physical world becomes increasingly close, their security issues have become more prominent. Such systems integrate hardware components such as sensors, processors, and actuators, as well as software modules such as perception algorithms, decision models, and control programs. In complex and dynamic environments, security vulnerabilities in any link may trigger a chain reaction. 展开更多
关键词 intelligent agents industrial production security dynamic learning embodied intelligence safety artificial intelligence
Call for PapersSpecial Issue on Security and Safety in Embodied Intelligence 认领 引用
16
《Security and Safety》 CSCD 2025年第4期170-170,共1页
Background As a key bridge connecting artificial intelligence and the physical world, embodied intelligence, by virtue of the real-time interaction, dynamic learning, and autonomous decision-making capabilities of int... Background As a key bridge connecting artificial intelligence and the physical world, embodied intelligence, by virtue of the real-time interaction, dynamic learning, and autonomous decision-making capabilities of intelligent agents with the environment, is rapidly penetrating into various scenarios such as industrial production, service industries, and family life. 展开更多
关键词 intelligent agents industrial production security dynamic learning embodied intelligence safety artificial intelligence
Special Section on Perception,Control,and Decision-Making of Embodied Intelligent Systems 认领 引用
17
《Journal of Systems Engineering and Electronics》 SCIE CSCD 2026年第1期F0002-F0002,共1页
Embodied intelligent systems integrate perception,control,and decision-making within physical agents,and have become a cornerstone of modern aerospace,autonomous driving,and cooperative robotic applications.When opera... Embodied intelligent systems integrate perception,control,and decision-making within physical agents,and have become a cornerstone of modern aerospace,autonomous driving,and cooperative robotic applications.When operating in uncertain and dynamic environments,such systems must address challenges arising from incomplete sensing,unpredictable maneuvers,communication constraints,disturbances,and evolving network structures. 展开更多
关键词 incomplete sensingunpredictable decision making embodied intelligent systems aerospaceautonomous drivingand control cooperative robotic applicationswhen evolving network structures perception
暂未订购 下载PDF
A Comprehensive Survey on Embodied Intelligence:Advancements,Challenges,and Future Perspectives 认领 引用 被引量：14
18
作者 Fuchun Sun Runfa Chen +3 位作者 Tianying Ji Yu Luo Huaidong Zhou Huaping Liu 《CAAI Artificial Intelligence Research》 2024年第1期31-55,共25页
Embodied Intelligence,which integrates physical interaction capabilities with cognitive computation in real-world scenarios,provides a promising path to achieve Artificial General Intelligence(AGI).Recently,the landsc... Embodied Intelligence,which integrates physical interaction capabilities with cognitive computation in real-world scenarios,provides a promising path to achieve Artificial General Intelligence(AGI).Recently,the landscape of embodied intelligence has grown profoundly,empowering robotics,autonomous driving,intelligent manufacturing,and so on.This paper presents a comprehensive survey on the evolution of embodied intelligence,tracing its journey from philosophical roots to contemporary advancements.We emphasize significant progress in the integration of perceptual,cognitive,and behavioral components,rather than focusing on these elements in isolation.Despite these advancements,several challenges remain,including hardware limitations,model generalization,physical world understanding,multimodal integration,and ethical considerations,which are critical for the development of robust and reliable embodied intelligence systems.To address these challenges,we outline future research directions,emphasizing Large Perception-Cognition-Behavior(PCB)models,physical intelligence,and morphological intelligence.Central to these perspectives is the general agent framework termed as Bcent,which integrates perception,cognition,and behavior dynamics.Bcent aims to enhance the adaptability,robustness,and intelligence of embodied systems,aligning with the ongoing progress in robotics,autonomous systems,healthcare,and more. 展开更多
关键词 embodied intelligence perception-cognition-behavior interactions general agent framework physical interaction
Training Methods and Generation Technologies for Embodied Intelligent Robot Manipulation Skill Models:A Systematic Review 认领 引用
19
作者 Lianpeng Li Zhoujun Ruan +4 位作者 Zhichuang Wang Haibo Zhang Hang Zhong Mingyang Li Chunpeng Kang 《Computers, Materials & Continua》 SCIE EI 2026年第10期33-62,共30页
Endowing embodied intelligent robots with dexterous manipulation capabilities is paramount for executing complex,open-ended tasks.These capabilities are foundational to advancing true robotic autonomy,thereby facilita... Endowing embodied intelligent robots with dexterous manipulation capabilities is paramount for executing complex,open-ended tasks.These capabilities are foundational to advancing true robotic autonomy,thereby facilitating precision assembly,seamless collaborative operations,and highly specialized maneuvers across diverse industrial and service sectors.Focusing on dynamic,unstructured environments where conventional programmed behaviors prove inadequate,this paper presents a systematic,quantitatively driven review of training methodologies and generation techniques for manipulation skill models within the domain of embodied artificial intelligence(AI).To provide rigorous trend validation,this study conducts a comprehensive bibliometric analysis and quantitative literature evaluation.By empirically mapping research distributions and methodological shifts across recent scholarly works,we substantiate our identification of mainstream research trajectories and developmental paradigms.This data-backed approach ensures the delineated landscape accurately reflects the consensus of the broader academic community,effectively mitigating subjective bias.Leveraging this validated framework,we rigorously analyze the core technical challenges currently hindering widespread deployment.These multifaceted challenges encompass high-dimensional nonlinear motion control,algorithmic sample inefficiencies,suboptimal reward formulations,the inherent semantic-to-physical alignment gap,and the computational constraints dictating large-scale applications.Furthermore,this review comprehensively examines key enabling technologies engineered to circumvent these barriers.Specifically,we systematically detail recent breakthroughs in motion control optimization,the evolution of advanced learning paradigms,complex task planning strategies,and synchronized multi-agent cooperative control frameworks.By critically evaluating these advancements,synthesizing the comparative efficacy of existing methodologies,and dissecting real-world deployment bottlenecks,this review establishes a robust theoretical foundation.Ultimately,it identifies practical,empirically supported pathways for future research to accelerate the transition of dexterous robotic manipulation from constrained laboratories to complex real-world applications. 展开更多
关键词 Embodied intelligent robots motion control advanced learning methods complex task planning mult-agent collaboration
暂未订购 下载PDF
Embodied Multi-Agent Systems:A Review 认领 引用 被引量：6
20
作者 Zhuo Li Weiran Wu +2 位作者 Yunlong Guo Jian Sun Qing-Long Han 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2025年第6期1095-1116,共22页
Multi-agent systems(MASs)have demonstrated significant achievements in a wide range of tasks,leveraging their capacity for coordination and adaptation within complex environments.Moreover,the enhancement of their inte... Multi-agent systems(MASs)have demonstrated significant achievements in a wide range of tasks,leveraging their capacity for coordination and adaptation within complex environments.Moreover,the enhancement of their intelligent functionalities is crucial for tackling increasingly challenging tasks.This goal resonates with a paradigm shift within the artificial intelligence(AI)community,from“internet AI”to“embodied AI”,and the MASs with embodied AI are referred to as embodied multi-agent systems(EMASs).An EMAS has the potential to acquire generalized competencies through interactions with environments,enabling it to effectively address a variety of tasks and thereby make a substantial contribution to the quest for artificial general intelligence.Despite the burgeoning interest in this domain,a comprehensive review of EMAS has been lacking.This paper offers analysis and synthesis for EMASs from a control perspective,conceptualizing each embodied agent as an entity equipped with a“brain”for decision and a“body”for environmental interaction.System designs are classified into open-loop,closed-loop,and double-loop categories,and EMAS implementations are discussed.Additionally,the current applications and challenges faced by EMASs are summarized and potential avenues for future research in this field are provided. 展开更多
关键词 Embodied intelligence multi-agent system feedback control interaction
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 3 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈