mlsanityData to 7 Oct 2026

Aerial and drone VLA

17 papers1 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: aerial, navigation, uav, onboard, flight

Key facts. Aerial and drone VLA: 17 papers on arXiv since 2025 (data through 7 Oct 2026). 7 of its 17 mapped papers (41%) cite “CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs” (2025, arXiv 2503.01378). 5 of its 17 mapped papers (29%) cite “VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments” (2025, arXiv 2512.15258). 3 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

3 new since 17 Sep

  1. WareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart Warehouses
  2. From Local Whole-Body VLA Behaviors to Scene-Scale Aerial Manipulation
  3. AeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations

Foundations

Most cited by papers here

  1. CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs2025cited by 7 here
  2. VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments2025cited by 5 here
  3. GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics2025cited by 3 here
  4. SINGER: An Onboard Generalist Vision-Language Navigation Policy for Drones2025cited by 2 here
  5. AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation2026cited by 2 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 10 here
  2. 2024Octo: An Open-Source Generalist Robot Policycited by 3 here
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 11 here
  4. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 1 here
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 7 here
  6. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 6 here
  7. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 2 here
  8. 2025VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environmentscited by 5 here
  9. 2026NavDreamer: Video Models as Zero-Shot 3D Navigatorscited by 2 here
  10. 2026UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Modelscited by 2 here
14 more it builds on, not in this chain
  1. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robotscited by 1 here
  2. 2024A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLMcited by 2 here
  3. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 3 here
  4. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 2 here
  5. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 2 here
  6. 2025CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVscited by 7 here
  7. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Modelcited by 2 here
  8. 2025GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamicscited by 3 here
  9. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 2 here
  10. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 2 here
  11. 2025SINGER: An Onboard Generalist Vision-Language Navigation Policy for Dronescited by 2 here
  12. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 2 here
  13. 2026AIR-VLA: Vision-Language-Action Systems for Aerial Manipulationcited by 2 here
  14. 2026Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmapcited by 2 here

The 24 most cited of 65.

Browse

12 of 17, ranked 6–17

  1. 6UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models20262
  2. 7Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap20262
  3. 8π, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation20261
  4. 9HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks20260
  5. 10LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception20260
  6. 11Exp2VLA: Enabling Vision-Language-Action for Drone Navigation from Expert Demonstrations20260
  7. 12Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review20260
  8. 13CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking20260
  9. 14RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation20260
  10. 15Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model20260
All 12
  1. 16Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching20260
  2. 17UnderwaterVLA: Dual-brain Vision-Language-Action architecture for Autonomous Underwater Navigation20250