集成技术2026，Vol.15Issue(3)：1-43,43.DOI:10.12146/j.issn.2095-3135.20250923001
跨模态交互驱动的具身智能:视觉-语言-动作融合模型、数据与平台综述
Cross-Modal Interaction-Driven Embodied Intelligence:A Review of Vision-Language-Action Models,Data,and Platforms
摘要
Abstract
The core of embodied intelligence is to enable an agent to perceive,understand,decide,and act in real or simulated environments through a"vision-language-action"loop,thereby acquiring transferable skill representations.Centered on this goal,the vision-language-action(VLA)paradigm is unifying visual representation,language reasoning,and action control within a single decision pipeline,and is gradually moving toward openness and reproducibility.First,this study examines embodied intelligence at the model level by evaluating planning-control hierarchical architectures against language/code-driven high-level task planners,and analyzes their differences in terms of generalization ability,interpretability,real-time deployability,and cross-morphology transferability.Then,at the data and evaluation level,we summarize cross-robot demonstration data and automated data collection pipelines,outline typical evaluation benchmarks(such as task success rate,long-horizon goal completion rate,and safety constraint metrics),and provide a minimal reproducible experimental protocol.Finally,at the platform level,we construct a"simulation-real robot-evaluation"loop that spans interactive simulation,GPU-parallelized physics-accelerated training,real-world robot validation,and unified evaluation standards,and we discuss its significance for Sim-to-Real deployment.On this basis,we further propose an analysis framework of"cross-modal interaction and alignment",which is used to characterize the error propagation pathways among perception,language understanding and planning,action generation,and environmental feedback.We then summarize the key future challenges and engineering roadmaps in areas such as data coverage,cross-modal robustness,energy efficiency,and safety governance.关键词
视觉-语言-动作模型/跨模态交互/具身智能/多模态大模型/数据集与基准测试/仿真平台/机器人应用Key words
vision-language-action models/cross-modal interaction/embodied intelligence/multimodal large models/datasets and benchmarks/simulation platforms/robotic applications分类
信息技术与安全科学引用本文复制引用
刘国华,崔纪泽,陆勇辰,胡军军,谢强,郭媛君,潘觅,杨之乐..跨模态交互驱动的具身智能:视觉-语言-动作融合模型、数据与平台综述[J].集成技术,2026,15(3):1-43,43.基金项目
深圳市优秀科技创新人才培养项目(RCYX20221008093036022) （RCYX20221008093036022）
深港联合资助项目(A 类)(SGDX20230116092053005) （A 类）
"广东特支计划"青年拔尖人才项目(2023TQ07L745,2024TQ08L818) （2023TQ07L745,2024TQ08L818）
韶关市"南岭团队计划"项目 This work is supported by Shenzhen Excellent Innovative Talents(RCYX20221008093036022),and Shenzhen-Hong Kong Jointly Funded Project(Type A)(SGDX20230116092053005),and Guangdong Special Support Plan for Young Top-Talent Project(2023TQ07L745,2024TQ08L818),and"Nanling Team Project"of Shaoguan city （RCYX20221008093036022）
