大型基础模型赋能下无人飞行器智能化：进展、应用与展望

doi:10.7527/S1000-6893.2026.33148

Abstract

Abstract:

Large Foundation Models （LFMs）， represented by large language models， vision language models， and vision foundation models， are driving a new wave of intelligent evolution for Unmanned Aerial Vehicles （UAVs）. Focusing on this trend， the key characteristics and general capabilities of relevant models are first summarized， followed by a categorization of the mainstream embodied architectures driven by them. A comparison is conducted regarding the adaptability and trade-offs of different architectures within the high-dynamic and strongly constrained scenarios of UAVs. Secondly， an analysis is provided on how various LFMs reshape the four core functional elements of UAVs， including perception， planning， control， and interaction， through mechanisms such as open-world understanding， task-level semantic planning， embodied reasoning control， and multi-modal interaction. Furthermore， focusing on high-level cognitive functions driven by LFMs， the mechanisms， implementation pathways， technical limitations， and evaluation paradigms of reasoning， memory， reflection， and imagination in coping with complex UAV scenarios are discussed. The empowerment patterns and frontier progress of LFMs in four typical decision-making tasks are then summarized， including vision-language navigation， active target search， semantic delivery， and swarm intelligent coordination. Finally， core challenges regarding safety risks and protection mechanisms， engineering implementation， and edge deployment are discussed， envisioning future directions in efficient foundation intelligence， the perception-to-cognition transition， and ubiquitous industrial collaboration.

Key words: intelligent UAVs, large foundation models, UAV decision-making tasks, embodied intelligence, higher-order cognition in agents

CLC Number:

Dian SHAO, Chu TANG, Min CHANG, Like LIU, Yule WANG, Hao LI, Junqiang BAI. Large foundation models empowering ummannod aerial vehicle intelligence: Progress, applications and perspectives[J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(15): 333148.

Figures/Tables 7

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

A systematic review of four typical UAV decision-making tasks： Comparative analysis covering benchmarks， evaluation metrics， representative works， LFM paradigms， deployment and validation

任务类型	代表基准和指标	方法	相关LFM	LFM赋能范式	模型部署平台	实验类型
视觉-语言导航（4.1节）	代表基准： AerialVLN、CityNav 常用指标： NE、SR、OSR、SPL、sDTW	STMR	GPT-4o （LLM）	指令+环境表征到动作推理	云（API）	仿真+ 实机
			Grounding DINO （VFM）	开放词汇目标检测	机载平台
			Tokenize Anything （VFM）	精细化语义分割	机载平台
		CityNavAgent	GPT-4V （VLM）	生成场景物体描述；多模态融合输出高层子目标	云（API）	仿真
			Grounding DINO （VFM）	开放词汇目标检测	本地服务器
			Segment Anything （VFM）	精细化语义分割	本地服务器
		GeoNav	GPT-3.5-turbo （LLM）	指令解析提取目标属性	云（API）	仿真
			GPT-4o （VLM）	构建分层场景图并导航	云（API）
			Grounding DINO （VFM）	开放词汇目标检测	本地服务器
			Segment Anything （VFM）	精细化语义分割	本地服务器
主动目标搜索（4.2节）	代表基准： OpenUAV、CityAVOS 常用指标：NE、SR、MSS、OSR、SPL	PRPSearcher	GPT-4o （VLM）	构建3D认知地图指导探索	云（API）	仿真
		PRPSearcher	Grounded-SAM （VFM）	精细化语义分割	本地服务器	仿真
		UAV-VLRR	GPT-4o （LLM）	指令解析提取目标类别	云（API）	仿真+ 实机
		UAV-VLRR	Molmo-7B （VLM）	像素级目标与障碍定位	本地服务器	仿真+ 实机
语义物流配送（4.3节）	代表基准： VLD 常用指标： SR、SPL、 Average Steps	LogisticsVLN	DeepSeek-R1-Distill-Qwen-14B （LLM）	CoT解析提取楼层与标志物	未提及（适用边/端侧部署）	仿真
语义物流配送（4.3节）	代表基准： VLD 常用指标： SR、SPL、 Average Steps	LogisticsVLN	Qwen2-VL-7B （VLM）	楼层估计/目标检测/探索	未提及（适用边/端侧部署）	仿真
集群智能协同（4.4节）	代表基准：模拟或现实环境常用指标：NASA-TLX、编队形状识别准确率、用户问卷	FlockGPT	GPT-4 （LLM）	由自然语言解析编队参数	云（API）	仿真+ 实机
		LLM-CRF	LLaVA-1.6 （VLM）	由视觉输入解析结构化语义	本地服务器	仿真
		LLM-CRF	Qwen-14B-Chat （LLM）	多模态融合生成包含摘要、推理链和可执行代码的可执行任务包	本地服务器	仿真

Table 1

Fig.5

Table 2

References 151

[1]	BARNHART R K， MARSHALL D M， SHAPPEE E. Introduction to unmanned aircraft systems （3rd ed.）［M］. Boca Raton： CRC Press， 2021： 56-70.
[2]	ZHANG W， GAO C， YU S， et al. CityNavAgent： Aerial vision-and-language navigation with hierarchical semantic planning and global memory［DB/OL］. arXiv Preprint： 2505.05622； 2025.
[3]	RAVICHANDRAN Z， MURALI V， TZES M， et al. SPINE： Online semantic planning for missions with incomplete natural language specifications in unstructured environments［C］∥2025 IEEE International Conference on Robotics and Automation （ICRA）. Piscataway： IEEE Press， 2025.
[4]	WANG X， YANG D， LIAO Y， et al. UAV-flow Colosseo： A real-world benchmark for flying-on-a-word UAV imitation learning［DB/OL］. arXiv Preprint： 2505.15725； 2025.
[5]	WANG Z， CHEN J， ZHENG X， et al. Hi AirStar， guide me to the badminton court［C］∥Proceedings of the 33rd ACM International Conference on Multimedia. New York： ACM， 2025.
[6]	LU P， PENG B， CHENG H， et al. Chameleon： Plug-and-play compositional reasoning with large language models［J］. Advances in Neural Information Processing Systems， 2023， 36： 43447-43478.
[7]	KE F， CAI Z， JAHANGARD S， et al. HYDRA： A hyper agent for dynamic compositional visual reasoning［C］∥LEONARDIS A， RICCI E， ROTH S， et al. Computer vision-ECCV 2024. Cham： Springer Nature Switzerland， 2025.
[8]	SHAH D J， RUSHTON P， SINGLA S， et al. Rethinking reflection in pre-training［DB/OL］. arXiv Preprint： 2504.04022； 2025.
[9]	YANG Z， YU X， CHEN D， et al. Machine mental imagery： Empower multimodal reasoning with latent visual tokens［DB/OL］. arXiv Preprint： 2506.17218； 2025.
[10]	DEVLIN J， CHANG M W， LEE K， et al. BERT： Pre-training of deep bidirectional transformers for language understanding［C］∥2019 Conference of the North American. Minneapolis： Association for Computational Linguistics， 2019.
[11]	RADFORD A， WU J， CHILD R， et al. Language models are unsupervised multitask learners［J］. OpenAI Blog， 2019， 1（8）： 9.
[12]	YANG Z， DAI Z， YANG Y， et al. XLNet： Generalized autoregressive pretraining for language understanding［J］. Advances in Neural Information Processing Systems， 2019， 32.
[13]	RAFFEL C， SHAZEER N， ROBERTS A， et al. Exploring the limits of transfer learning with a unified text-to-text transformer［J］. Journal of Machine Learning Research， 2020， 21（140）： 1-67.
[14]	OPENAI. Introducing GPT-5［EB/OL］. （2025-09-02）［2025-11-27］. .
[15]	Introducing OpenAI o 3 and o4 -mini［EB/OL］. （2025-04-16）［2025-11-27］. .
[16]	ANTHROPIC. Introducing Claude 4［EB/OL］. （2025-05-22）［2025-11-27］. .
[17]	GUO D， YANG D， ZHANG H， et al. Deepseek-r1： Incentivizing reasoning capability in LLMs via reinforcement learning［DB/OL］. arXiv Preprint： 2501.12948； 2025.
[18]	YANG A， LI A， YANG B， et al. Qwen3 technical report［DB/OL］. arXiv Preprint： 2505.09388； 2025.
[19]	BROWN T， MANN B， RYDER N， et al. Language models are few-shot learners［J］. Advances in Neural Information Processing Systems， 2020， 33： 1877-1901.
[20]	WEI J， WANG X， SCHUURMANS D， et al. Chain-of-thought prompting elicits reasoning in large language models［J］. Advances in Neural Information Processing Systems， 2022， 35： 24824-24837.
[21]	SHAZEER N， MIRHOSEINI A， MAZIARZ K， et al. Outrageously large neural networks： The sparsely-gated mixture-of-experts layer［DB/OL］. arXiv Preprint： 1701.06538； 2017.
[22]	TAN H， BANSAL M. LXMERT： Learning cross-modality encoder representations from transformers［DB/OL］. arXiv Preprint： 1908.07490； 2019.
[23]	LI X， YIN X， LI C， et al. Oscar： Object-semantics aligned pre-training for vision-language tasks［C］∥Computer Vision-ECCV 2020. Cham： Springer International Publishing， 2020.
[24]	CHEN Y C， LI L， YU L， et al. UNITER： UNiversal image-TExt representation learning［C］∥Computer Vision-ECCV 2020. Cham： Springer Cham， 2020.
[25]	SUN C， MYERS A， VONDRICK C， et al. VideoBERT： A joint model for video and language representation learning［C］∥Proceedings of the IEEE/CVF international conference on computer vision. Piscataway： IEEE Press， 2019.
[26]	LI L H， YATSKAR M， YIN D， et al. VisualBERT： A simple and performant baseline for vision and language［DB/OL］. arXiv Preprint： 1908.03557； 2019.
[27]	LIU H T， LI C Y， WU Q Y， et al. Visual instruction tuning［J］. Advances in Neural Information Processing Systems， 2023， 36： 34892-34916.
[28]	ALAYRAC J B， DONAHUE J， LUC P， et al. Flamingo： A visual language model for few-shot learning［J］. Advances in Neural Information Processing Systems， 2022， 35： 23716-23736.
[29]	LI J， LI D， XIONG C， et al. BLIP： Bootstrapping language-image pre-training for unified vision-language understanding and generation［C］∥International conference on machine learning. New York： PMLR， 2022.
[30]	RADFORD A， KIM J W， HALLACY C， et al. Learning transferable visual models from natural language supervision［C］∥International conference on machine learning. New York： PMLR， 2021.
[31]	DOSOVITSKIY A. An image is worth 16×16 words： Transformers for image recognition at scale［DB/OL］. arXiv Preprint： 2010.11929； 2020.
[32]	OPENAI. GPT-4V（ision） system card［EB/OL］. （2025-08-25）［2025-11-27］. .
[33]	HURST A， LERER A， GOUCHER A P， et al. Gpt-4o system card［DB/OL］. arXiv Preprint： 2410.21276； 2024.
[34]	ANTHROPIC. Introducing the next generation of Claude［EB/OL］. （2025-08-27）［2025-11-27］. .
[35]	COMANICI G， BIEBER E， SCHAEKERMANN M， et al. Gemini 2.5： Pushing the frontier with advanced reasoning， multimodality， long context， and next generation agentic capabilities［DB/OL］. arXiv Preprint： 2507.06261； 2025.
[36]	BAI J， BAI S， YANG S， et al. Qwen-VL： A versatile vision-language model for understanding， localization， text reading， and beyond［DB/OL］. arXiv Preprint： 2308.12966； 2023.
[37]	CHEN Z， WU J， WANG W， et al. InternVL： Scaling up vision foundation models and aligning for generic visual-linguistic tasks［C］∥Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Piscataway： IEEE Press， 2024.
[38]	WANG W， LV Q， YU W， et al. CogVLM： Visual expert for pretrained language models［J］. Advances in Neural Information Processing Systems， 2024， 37： 121475-121499.
[39]	CARON M， TOUVRON H， MISRA I， et al. Emerging properties in self-supervised vision transformers［C］∥Proceedings of the IEEE/CVF international conference on computer vision. Piscataway： IEEE Press， 2021.
[40]	CARON M， TOUVRON H， MISRA I， et al. Emerging properties in self-supervised vision transformers［C］∥Proceedings of the IEEE/CVF international conference on computer vision. Piscataway： IEEE Press， 2021.
[41]	OQUAB M， DARCET T， MOUTAKANNI T， et al. Dinov2： Learning robust visual features without supervision［DB/OL］. arXiv Preprint： 2304.07193； 2023.
[42]	KIRILLOV A， MINTUN E， RAVI N， et al. Segment anything［C］∥Proceedings of the IEEE/CVF international conference on computer vision. Piscataway： IEEE Press， 2023.
[43]	LI L H， ZHANG P， ZHANG H， et al. Grounded language-image pre-training［C］∥Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Piscataway： IEEE Press， 2022.
[44]	CHENG T， SONG L， GE Y， et al. Yolo-world： Real-time open-vocabulary object detection［C］∥Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Piscataway： IEEE Press， 2024.
[45]	LIU S， ZENG Z， REN T， et al. Grounding DINO： Marrying DINO with grounded pre-training for open-set object detection［C］∥Computer Vision-ECCV 2024. Cham： Springer Cham， 2025.
[46]	LÜDDECKE T， ECKER A. Image segmentation using text and image prompts［C］∥Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Piscataway： IEEE Press， 2022.
[47]	YUAN H， LI X， ZHOU C， et al. Open-vocabulary SAM： Segment and recognize twenty-thousand classes interactively［C］∥Computer Vision-ECCV 2024. Cham： Springer Cham， 2025.
[48]	WANG X， ZHANG X， CAO Y， et al. SegGPT： towards segmenting everything in context［C］∥Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE Press， 2023.
[49]	ZOU X， YANG J， ZHANG H， et al. Segment everything everywhere all at once［J］. Advances in Neural Information Processing Systems， 2023， 36： 19769-19782.
[50]	BHAT S F， BIRKL R， WOFK D， et al. ZoeDepth： Zero-shot transfer by combining relative and metric depth［DB/OL］. arXiv Preprint： 2302.12288； 2023.
[51]	YANG L， KANG B， HUANG Z， et al. Depth anything： Unleashing the power of large-scale unlabeled data［C］∥Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Piscataway： IEEE Press， 2024.
[52]	BOCHKOVSKII A， DELAUNOY A， GERMAIN H， et al. Depth pro： Sharp monocular metric depth in less than a second［DB/OL］. arXiv Preprint： 2410.02073； 2024.
[53]	ZITKOVICH B， YU T， XU S， et al. Rt-2： Vision-language-action models transfer web knowledge to robotic control［C］∥Conference on Robot Learning. New York： PMLR， 2023.
[54]	KIM M J， PERTSCH K， KARAMCHETI S， et al. Openvla： An open-source vision-language-action model［DB/OL］. arXiv Preprint： 2406.09246； 2024.
[55]	WEN J， ZHU Y， LI J， et al. TinyVLA： Toward fast， data-efficient vision-language-action models for robotic manipulation［J］. IEEE Robotics and Automation Letters， 2025， 10（4）： 3988-3995.
[56]	MEI A， ZHU G N， ZHANG H， et al. ReplanVLM： Replanning robotic tasks with visual language models［J］. IEEE Robotics and Automation Letters， 2024， 9（11）： 10201-10208.
[57]	SKRETA M， ZHOU Z， YUAN J L， et al. Replan： Robotic replanning with perception and language models［DB/OL］. arXiv Preprint： 2401.04157； 2024.
[58]	AO S， SALIM F D， KHAN S. EMAC+： Embodied multimodal agent for collaborative planning with VLM+ LLM［DB/OL］. arXiv Preprint： 2505.19905； 2025.
[59]	ZHAO Q， LU Y， KIM M J， et al. Cot-vla： Visual chain-of-thought reasoning for vision-language-action models［C］∥Proceedings of the Computer Vision and Pattern Recognition Conference. Piscataway： IEEE Press， 2025.
[60]	SUN Q， HONG P， PALA T D， et al. Emma-X： An embodied multimodal action model with grounded chain of thought and look-ahead spatial reasoning［C］∥63rd Annual Meeting of the Association for Computational Linguistics Vienna： Association for Computational Linguistics， 2025.
[61]	LIN F， NAI R， HU Y， et al. OneTwoVLA： A unified vision-language-action model with adaptive reasoning［DB/OL］. arXiv Preprint： 2505.11917； 2025.
[62]	SERPIVA V， LYKOV A， MYSHLYAEV A， et al. RaceVLA： VLA-based racing drone navigation with human-like behaviour［DB/OL］. arXiv Preprint： 2503.02572； 2025.
[63]	HE K， ZHANG X， REN S， et al. Deep residual learning for image recognition［C］∥Proceedings of the IEEE conference on computer vision and pattern recognition. Piscataway： IEEE Press， 2016.
[64]	HUSSAIN M. YOLO-v1 to YOLO-v8， the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection［J］. Machines， 2023， 11（7）： 677.
[65]	REN S， HE K， GIRSHICK R， et al. Faster R-CNN： Towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2016， 39（6）： 1137-1149.
[66]	ZHANG X， TIAN Y， LIN F， et al. LogisticsVLN： Vision-language navigation for low-altitude terminal delivery based on agentic UAVs［DB/OL］. arXiv Preprint： 2505.03460； 2025.
[67]	HART P E， NILSSON N J， RAPHAEL B. A formal basis for the heuristic determination of minimum cost paths［J］. IEEE transactions on Systems Science and Cybernetics， 1968， 4（2）： 100-107.
[68]	LAVALLE S. Rapidly-exploring random trees： A new tool for path planning［R］. Research Report 9811， 1998.
[69]	SHAH D， OSIŃSKI B， LEVINE S， et al. Lm-nav： Robotic navigation with large pre-trained models of language， vision， and action［C］∥Conference on robot learning. New York： PMLR， 2023.
[70]	AHN M， BROHAN A， BROWN N， et al. Do as I can， not as I say： Grounding language in robotic affordances［DB/OL］. arXiv Preprint： 2204.01691； 2022.
[71]	XIAO J， TSAO C W， ZHANG Y， et al. FM-planner： Foundation model guided path planning for autonomous drone navigation［DB/OL］. arXiv Preprint： 2505.20783； 2025.
[72]	BAI J， BAI S， CHU Y， et al. Qwen technical report［DB/OL］. arXiv Preprint： 2309.16609； 2023.
[73]	TEAM G， MESNARD T， HARDIN C， et al. Gemma： Open models based on Gemini research and technology［DB/OL］. arXiv Preprint： 2403.08295； 2024.
[74]	DUBEY A， JAUHRI A， PANDEY A， et al. The llama 3 herd of models［DB/OL］. arXiv Preprint： 2407.21783； 2024.
[75]	WATKINS C J， DAYAN P. Q-learning［J］. Machine learning， 1992， 8（3-4）： 279-292.
[76]	CHEN G， YU X， LING N， et al. TypeFly： Flying drones with large language model［DB/OL］. arXiv Preprint： 2312.14950； 2023.
[77]	TAGLIABUE A， KONDO K， ZHAO T， et al. REAL： Resilience and adaptation using large language models on autonomous aerial robots［C］∥2024 IEEE 63rd Conference on Decision and Control （CDC）. Piscataway： IEEE Press， 2024.
[78]	WANG W， LI Y， JIAO L， et al. GSCE： A prompt framework with enhanced reasoning for reliable LLM-driven drone control［C］∥2025 International Conference on Unmanned Aircraft Systems （ICUAS）. Piscataway： IEEE Press， 2025.
[79]	YOO M， NA Y， SONG H， et al. Motion estimation and hand gesture recognition-based human-UAV interaction approach in real time［J］. Sensors， 2022， 22（7）： 2513.
[80]	万开方，吴志林，武韫晖，等. 拒止环境下基于深度强化学习的多无人机协同定位［J］. 航空学报， 2025， 46（8）： 331024.
	WAN K F， WU Z L， WU Y H， et al. Multi-UAV cooperative localization based on deep reinforcement learning in denied environments［J］. Acta Aeronautica et Astronautica Sinica， 2025， 46（8）： 331024 （in Chinese）.
[81]	CLADERA F， RAVICHANDRAN Z， HUGHES J， et al. Air-ground collaboration for language-specified missions in unknown environments［DB/OL］. arXiv Preprint： 2505.09108； 2025.
[82]	RAVICHANDRAN Z， CLADERA F， HUGHES J， et al. Deploying foundation model-enabled air and ground robots in the field： Challenges and opportunities［DB/OL］. arXiv Preprint： 2505.09477； 2025.
[83]	LYKOV A， KARAF S， MARTYNOV M， et al. FlockGPT： Guiding UAV flocking with linguistic orchestration［C］∥2024 IEEE International Symposium on Mixed and Augmented Reality Adjunct （ISMAR-Adjunct）. Piscataway： IEEE Press， 2024.
[84]	DHARMALINGAM B， MUKHERJEE R， PIGGOTT B， et al. Aero-LLM： A distributed framework for secure UAV communication and intelligent decision-making［DB/OL］. arXiv Preprint： 2502.05220； 2025.
[85]	DAI S， MA Z， LUO Z， et al. MM-UAVBench： How well do multimodal large language models see， think， and plan in low-altitude UAV scenarios？［DB/OL］. arXiv Preprint： 2512.23219； 2025.
[86]	ZHU Z， XUE Y， CHEN X， et al. Large language models can learn rules［DB/OL］. arXiv Preprint： 2310.07064； 2023.
[87]	HAO S B， GU Y， MA H D， et al. Reasoning with language model is planning with world model［DB/OL］. arXiv Preprint： 2305.14992； 2023.
[88]	MOWER C E， WAN Y， YU H， et al. ROS-LLM： A ros framework for embodied ai with task feedback and structured reasoning［DB/OL］. arXiv Preprint： 2406.19741； 2024.
[89]	ZHANG W， WANG M， LIU G， et al. Embodied-reasoner： Synergizing visual search， reasoning， and action for embodied interactive tasks［DB/OL］. arXiv Preprint： 2503.21696； 2025.
[90]	CAI Z， CARDENAS C R， LEO K， et al. NEUSIS： A compositional neuro-symbolic framework for autonomous perception， reasoning， and planning in complex UAV search missions［J］. IEEE Robotics and Automation Letters， 2025， 10（9）： 9502-9509.
[91]	GAO Y， WANG Z， JING L， et al. Aerial vision-and-language navigation via semantic-topo-metric representation guided LLM reasoning［DB/OL］. arXiv Preprint： 2410.08500； 2024.
[92]	ZHAO J， LIN X. General-purpose aerial intelligent agents empowered by large language models［DB/OL］. arXiv Preprint： 2503.08302； 2025.
[93]	ZHAO B， WANG Z， FANG J， et al. Embodied-R： Collaborative framework for activating embodied spatial reasoning in foundation models via reinforcement learning［C］∥Proceedings of the 33rd ACM International Conference on Multimedia. New York： ACM， 2025.
[94]	WANG G， XIE Y， JIANG Y， et al. Voyager： An open-ended embodied agent with large language models［DB/OL］. arXiv Preprint： 2305.16291； 2023.
[95]	WANG Z， LI X， YANG J， et al. Gridmm： Grid memory map for vision-and-language navigation［C］∥Proceedings of the IEEE/CVF International conference on computer vision. Piscataway： IEEE Press， 2023.
[96]	LI H， WANG Z， YANG X， et al. Memonav： Working memory model for visual navigation［C］∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2024.
[97]	ZHENG Q， LIU D， WANG C， et al. Esceme： Vision-and-language navigation with episodic scene memory［J］. International Journal of Computer Vision， 2025， 133（1）： 254-274.
[98]	ZENG Q， YANG Q， DONG S， et al. Perceive， reflect， and plan： Designing LLM agent for goal-directed city navigation without instructions［DB/OL］. arXiv Preprint： 2408.04168； 2024.
[99]	LINGO R， ARROYO M， CHHAJER R. Enhancing LLM problem solving with reap： Reflection， explicit problem deconstruction， and advanced prompting［DB/OL］. arXiv Preprint： 2409.09415； 2024.
[100]	YANG Z， LIU J， CHEN P， et al. RILA： Reflective and imaginative language agent for zero-shot semantic audio-visual navigation［C］∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2024.
[101]	YU Z， LONG Y， YANG Z， et al. CorrectNav： Self-correction Flywheel empowers vision-language-action navigation model［DB/OL］. arXiv Preprint： 2508.10416； 2025.
[102]	HUANG Y， WU M， LI R， et al. VISTA： Generative visual imagination for vision-and-language navigation［DB/OL］. arXiv Preprint： 2505.07868； 2025.
[103]	PERINCHERRY A， KRANTZ J， LEE S. Do visual imaginations improve vision-and-language navigation agents？［C］∥Proceedings of the Computer Vision and Pattern Recognition Conference. Piscataway： IEEE Press， 2025.
[104]	ANDERSON P， WU Q， TENEY D， et al. Vision-and-language navigation： Interpreting visually-grounded navigation instructions in real environments［C］∥Proceedings of the IEEE conference on computer vision and pattern recognition. Piscataway： IEEE Press， 2018.
[105]	KU A， ANDERSON P， PATEL R， et al. Room-across-room： Multilingual vision-and-language navigation with dense spatiotemporal grounding［DB/OL］. arXiv Preprint： 2010.07954； 2020.
[106]	CHEN H， SUHR A， MISRA D， et al. Touchdown： Natural language navigation and spatial reasoning in visual street environments［C］∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2019.
[107]	LEE J， MIYANISHI T， KURITA S， et al. CityNav： Language-goal aerial navigation dataset with geographic information［DB/OL］. arXiv Preprint： 2406.14240； 2024.
[108]	DORBALA V S， SIGURDSSON G， PIRAMUTHU R， et al. CLIP-Nav： Using clip for zero-shot vision-and-language navigation［DB/OL］. arXiv Preprint： 2211.16649； 2022.
[109]	DORBALA V S， MULLEN JR J F， MANOCHA D. Can an embodied agent find your “cat-shaped mug”？ LLM-based zero-shot object navigation［DB/OL］. arXiv Preprint： 2303.03480； 2023.
[110]	ZHOU G， HONG Y， WU Q. NavGPT： Explicit reasoning in vision-and-language navigation with large language models［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2024， 38（7）： 7641-7649.
[111]	LONG Y， LI X， CAI W， et al. Discuss before moving： Visual language navigation via multi-expert discussions［C］∥2024 IEEE International Conference on Robotics and Automation （ICRA）. Piscataway： IEEE Press， 2024.
[112]	LONG Y， CAI W， WANG H， et al. InstructNav： Zero-shot system for generic instruction navigation in unexplored environment［DB/OL］. arXiv Preprint： 2406.04882； 2024.
[113]	ZHOU G， HONG Y， WANG Z， et al. NavGPT-2： Unleashing navigational reasoning capability for large vision-language models［C］∥Computer Vision-ECCV 2024. Cham： Springer Cham， 2025.
[114]	SU Y， AN D， CHEN K， et al. Learning fine-grained alignment for aerial vision-dialog navigation［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2025， 39（7）： 7060-7068.
[115]	XU H， HU Y， GAO C， et al. GeoNav： Empowering MLLMs with explicit geospatial reasoning abilities for language-goal aerial navigation［DB/OL］. arXiv Preprint： 2504.09587； 2025.
[116]	ZHAO G， LI G， PAN J， et al. Aerial vision-and-language navigation with grid-based view selection and map construction［DB/OL］. arXiv Preprint： 2503.11091； 2025.
[117]	LIN H， YANG X， WEN G， et al. Fast UAV object-searching in large-scale and complex environments［J］. IEEE Transactions on Cybernetics， 2025， 55（6）： 2993-3004.
[118]	CHANGOLUISA CAIZA I D， MILAS A， MONTES GROVA M A， et al. Autonomous exploration of unknown 3D environments using a frontier-based collector strategy［C］∥2024 IEEE International Conference on Robotics and Automation （ICRA）. Piscataway： IEEE Press， 2024.
[119]	PAPAIOANNOU S， KOLIOS P， THEOCHARIDES T， et al. 3D trajectory planning for UAV-based search missions： An integrated assessment and search planning approach［C］∥2021 International Conference on Unmanned Aircraft Systems （ICUAS）. Piscataway： IEEE Press， 2021.
[120]	BARTOLOMEI L， TEIXEIRA L， CHLI M. Fast multi-UAV decentralized exploration of forests［J］. IEEE Robotics and Automation Letters， 2023， 8（9）： 5576-5583.
[121]	SANDINO J， CACCETTA P A， SANDERSON C， et al. Reducing object detection uncertainty from RGB and thermal data for UAV outdoor surveillance［C］∥2022 IEEE Aerospace Conference （AERO）. Piscataway： IEEE Press， 2022.
[122]	GUPTA A， BESSONOV D， LI P. A decision-theoretic approach to detection-based target search with a UAV［C］∥2017 IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. Piscataway： IEEE Press， 2017.
[123]	XU K， ZHENG L， WEI M， et al. VRExplorer： An efficient view-region based autonomous exploration method in unknown environments for UAV［C］∥2024 IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. Piscataway： IEEE Press， 2024.
[124]	YAN P， JIA T， BAI C C. Searching and tracking an unknown number of targets： A learning-based method enhanced with maps merging［J］. Sensors， 2021， 21（4）： 1076.
[125]	YAQOOT Y， MUSTAFA M A， SAUTENKOV O， et al. UAV-VLRR Vision-language informed nmpc for rapid response in UAV search and rescue［DB/OL］. arXiv Preprint： 2503.02465； 2025.
[126]	JI Y， ZHU Z， ZHAO Y， et al. Towards autonomous UAV visual object search in city space： Benchmark and agentic methodology［DB/OL］. arXiv Preprint： 2505.08765； 2025.
[127]	TIAN Y， LIN F， ZHANG X， et al. LogisticsVISTA： 3D terminal delivery services with UAVs， UGVs and USVs based on foundation models and scenarios engineering［C］∥2024 IEEE International Conference on Service Operations and Logistics， and Informatics （SOLI）. Piscataway： IEEE Press， 2024.
[128]	于彦鹏，余墨多，汤奇荣，等. 面向城市应急物资配送的多无人机协同路径规划算法［J］. 控制与决策， 2025， 40（4）： 1098-1106.
	YU Y P， YU M D， TANG Q R， et al. Multi-UAV cooperative path planning algorithm for urban emergency logistics distribution ［J］. Control and Decision， 2025， 40（4）： 1098-1106 （in Chinese）.
[129]	张启钱，许卫卫，张洪海，等. 复杂低空物流无人机路径规划［J］. 北京航空航天大学学报， 2020， 46（7）： 1275-1286.
	ZHANG Q Q， XU W W， ZHANG H H， et al. Path planning for low-altitude logistics UAVs in complex environments ［J］. Journal of Beijing University of Aeronautics and Astronautics， 2020， 46（7）： 1275-1286 （in Chinese）.
[130]	YAO Y， LUO S， ZHAO H， et al. Can LLM substitute human labeling？ A case study of fine-grained chinese address entity recognition dataset for UAV delivery［C］∥Companion Proceedings of the ACM Web Conference 2024.New York： ACM， 2024.
[131]	ZHOU B， XU H， SHEN S. Racer： Rapid collaborative exploration with a decentralized multi-UAV system［J］. IEEE Transactions on Robotics， 2023， 39（3）： 1816-1835.
[132]	PAPYAN N， KULHANDJIAN M， KULHANDJIAN H， et al. AI-based drone assisted human rescue in disaster environments： Challenges and opportunities［J］. Pattern Recognition and Image Analysis， 2024， 34（1）： 169-186.
[133]	PUEYO P， MONTIJANO E， MURILLO A C， et al. CLIPSwarm： Generating drone shows from text prompts with vision-language models［C］∥2024 IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. Piscataway： IEEE Press， 2024.
[134]	ZHANG T， TIAN Y， LIN F， et al. CoordField： Coordination field for agentic UAV task allocation in low-altitude urban scenarios［DB/OL］. arXiv Preprint： 2505.00091； 2025.
[135]	LIN F， ZHANG T， NI Q， et al. Talk less， fly lighter： Autonomous semantic compression for UAV swarm communication via LLMs［DB/OL］. arXiv Preprint： 2508.12043； 2025.
[136]	JI K， HU X， ZHANG X， et al. An LLM-based framework for human-swarm teaming cognition in disaster search and rescue［DB/OL］. arXiv Preprint： 2511.04042； 2025.
[137]	KRINNER M， ROMERO A， BAUERSFELD L， et al. MPCC++： Model predictive contouring control for time-optimal flight with safety constraints［DB/OL］. arXiv Preprint： 2403.17551； 2024.
[138]	BUI D N， KHUAT T H， PHUNG M D， et al. Model predictive control for optimal motion planning of unmanned aerial vehicles［C］∥2024 International Conference on Control， Robotics and Informatics （ICCRI）. Piscataway： IEEE Press， 2024.
[139]	BOUCHEKIR R， GUZMAN M， COOK A， et al. Formal verification for safe AI-based flight planning for UAVs*［C］∥2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops （DSN-W）. Piscataway： IEEE Press， 2023.
[140]	TANG Y C， CHEN P Y， HO T Y. Defining and evaluating physical safety for large language models［DB/OL］. arXiv Preprint： 2411.02317； 2024.
[141]	SUN Y， CHEN Y， WU P， et al. DRL： Dynamic rebalance learning for adversarial robustness of UAV with long-tailed distribution［J］. Computer Communications， 2023， 205： 14-23.
[142]	REN Y， ZHU F， LU G， et al. Safety-assured high-speed navigation for MAVs［J］. Science Robotics， 2025， 10（98）： eado6187.
[143]	BADAR A U R， MAHMOOD D， IQBAL A， et al. DeepSpoofNet： A framework for securing UAVs against GPS spoofing attacks［J］. PeerJ Computer Science， 2025， 11： e2714.
[144]	NVIDIA jetson AGX orin［EB/OL］. （2025-10-28）［2025-11-27］. .
[145]	Atlas 200I A2［EB/OL］. （2025-11-12）［2025-11-27］. .
[146]	RK3588［EB/OL］. （2025-08-08）［2025-11-27］. .
[147]	AR9481［EB/OL］. （2021-12-20）［2025-11-27］. .
[148]	MCENROE P， WANG S， LIYANAGE M. A survey on the convergence of edge computing and AI for UAVs： Opportunities and challenges［J］. IEEE Internet of Things Journal， 2022， 9（17）： 15435-15459.
[149]	XU J， LI Z， CHEN W， et al. On-device language models： A comprehensive review［DB/OL］. arXiv Preprint： 2409.00088； 2024.
[150]	LIN J， TANG J， TANG H， et al. Awq： Activation-aware weight quantization for on-device llm compression and acceleration［J］. Proceedings of Machine Learning and Systems， 2024， 6： 87-100.
[151]	GU A， DAO T. Mamba： Linear-time sequence modeling with selective state spaces［DB/OL］. arXiv Preprint： 2312.00752； 2023.

平台厂商	芯片型号	算力/TOPS	显存/GB	功耗/W	可用模型规模/B
英伟达	AGX Orin	275	32/64	15~60	≤70
	Orin NX	157	8/16	10~40	≤14
	Orin Nano	67	4/8	7~25	≤4
华为昇腾	Atlas 200I A2	20	4/8/12	25	≤7
瑞芯	RK3588	6	8~16	2~10	≤10
酷芯	AR9481	8		1	≤1

Large foundation models empowering ummannod aerial vehicle intelligence: Progress, applications and perspectives

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 151

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	. The Research on High-Precision Reconstruction of Sampling Areas for Exogenous Cameras in Mars Sampling Missions [J]. Acta Aeronautica et Astronautica Sinica, 0, (): 1-0.
[2]	. A Multi-source Autonomous Calibration Method for Asteroid Exploration [J]. Acta Aeronautica et Astronautica Sinica, 0, (): 1-0.
[3]	Lei ZHOU, Yanfeng GU, Tianzhu LIU. Aircraft fine-grained object detection algorithm in remote sensing images [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(10): 632578-632578.
[4]	. Physics-Guided Geometric Verification for UAV Visual Localization under Weak-Texture Conditions [J]. Acta Aeronautica et Astronautica Sinica, 0, (): 1-0.
[5]	Zhenyang HAO, Shang CAO, Fengting ZHANG, Lanlan HOU. Design of a hub-mounted active actuation system for helicopters [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(7): 432464-432464.
[6]	Yao ZHAO, Xi ZHANG, Di ZHOU, Yutang LI, Siyuan LI. Rapid reentry trajectory planning for hypersonic vehicles with proactive no-fly zone separation assurance [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(6): 332509-332509.
[7]	Zheng WANG, Shouzhi ZHAO, Haotian LI, Zheng SUN, Jing SHAO, Cheng HOU. Development status of ice-penetrating probes for deep space exploration [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(5): 332398-332398.
[8]	. Resilient Networking and Reconfiguration Method for Satellite Networks Oriented to Single Event Effects [J]. Acta Aeronautica et Astronautica Sinica, 0, (): 1-0.
[9]	Fei TAO, He ZHANG, Weiran LIU, Chenyuan ZHANG, Yupeng WEI, Li YI, Xiaofu ZOU. Theories and key technologies of digital experiment and validation for aerospace equipment [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(24): 432516-432516.
[10]	Liang CHEN, Fanxing MENG, Chengbo WANG, Yinxuan ZHANG, Linshu MENG. Development and application of digital twins technology in aircraft strength design [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 532252-532252.
[11]	Tong LIU, Wenxiang ZHAO, Jinghua JI. Review of computational methods for electromagnetic vibration and noise in inverter-fed permanent magnet synchronous machines [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(1): 332127-332127.
[12]	Fan PU, Zhijie CHEN, Yang LIU, Xin GENG, Yongwen ZHU, Kejin REN. Air traffic management technologies for digital low-altitude integrated operations [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(11): 531331-531331.
[13]	Honglin LIU, Guan WANG, Shuaibin AN, Shaojie MA, Kai LIU. Online identification based strong adaptive control of hypersonic morphing vehicles [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(17): 331654-331654.
[14]	Shusheng CHEN, Muliang JIA, Jiahao LIN, Shiyi JIN, Zhenghong GAO, Yueqing WANG, Zhiqiang MA, Zheng LI, Chenlong DUAN, Jiawei LI. Empowering aircraft technology applications with generative models: Research progress and prospects [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(10): 631194-631194.
[15]	Jie LIN, Zhigong TANG, Weiqi QIAN, Yueqing WANG, Peng ZHANG, Weixia XU, Jie LIU. Research progress and prospects of aircraft aerodynamic design based on generative models [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(10): 631679-631679.