mlsanityData to 7 Oct 2026

CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs

arXiv 2503.01378 ↗First posted 3 Mar 2025cs.ROcited by 21

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

This paper introduces CognitiveDrone, a novel Vision-Language-Action (VLA) model tailored for complex Unmanned Aerial Vehicles (UAVs) tasks that demand advanced cognitive abilities. Trained on a dataset comprising over 8,000 simulated flight trajectories across three key categories-Human Recognition, Symbol Understanding, and Reasoning-the model generates real-time 4D action commands based on first-person visual inputs and textual instructions. To further enhance performance in intricate scenarios, we propose CognitiveDrone-R1, which integrates an additional Vision-Language Model (VLM) reasoning module to simplify task directives prior to high-frequency control. Experimental evaluations using our open-source benchmark, CognitiveDroneBench, reveal that while a racing-oriented model (RaceVLA) achieves an overall success rate of 31.3%, the base CognitiveDrone model reaches 59.6%, and CognitiveDrone-R1 attains a success rate of 77.2%. These results demonstrate improvements of up to 30% in critical cognitive tasks, underscoring the effectiveness of incorporating advanced reasoning capabilities into UAV control systems. Our contributions include the development of a state-of-the-art VLA model for UAV control and the introduction of the first dedicated benchmark for assessing cognitive tasks in drone operations. The complete repository is available at cognitivedrone.github.io

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 19 of its 27 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

19 of 27 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks31 Oct
  2. 2024Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation11 Oct

Other references · 17

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  3. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  4. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  6. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  7. 2023ChatGPT for Robotics: Design Principles and Model Abilitiescited by 296
  8. 2024VLP: Vision Language Planning for Autonomous Drivingcited by 125
  9. 2023AerialVLN: Vision-and-Language Navigation for UAVscited by 117
  10. 2024Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodologycited by 92
  11. 2022Aerial Vision-and-Dialog Navigationcited by 48
  12. 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobilitycited by 48
5 more
  1. 2025UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generationcited by 27
  2. 2023Swarm-GPT: Combining Large Language Models with Safe Motion Planning for Robot Choreography Designcited by 15
  3. 2023A Safer Vision-based Autonomous Planning System for Quadrotor UAVs with Dynamic Obstacle Trajectory Prediction and Its Application with LLMscited by 13
  4. 2024Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Modelscited by 8
  5. 2024CognitiveOS: Large Multimodal Model based System to Endow Any Type of Robot with Generative AIcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 13.

21 papers.

Sort:

By area:

  1. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  2. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  3. 2025See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigationcited by 18
  4. 2025GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamicscited by 14
  5. 2026AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Controlcited by 11
  6. 2025UAV-CodeAgents: Scalable UAV Mission Planning via Multi-Agent ReAct and Vision-Language Reasoningcited by 7
  7. 2026AIR-VLA: Vision-Language-Action Systems for Aerial Manipulationcited by 6
  8. 2026APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigationcited by 5
  9. 2025Bring the Apple, Not the Sofa: Impact of Irrelevant Context in Embodied AI Commands on VLA Modelscited by 4
  10. 2026UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Modelscited by 4
  11. 2026ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescuecited by 4
  12. 2025Embodied4C: Measuring What Matters for Embodied Vision-Language Navigationcited by 3
9 more
  1. 2025AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Modelscited by 1
  2. 2026CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Trackingcited by 1
  3. 2026AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimizationcited by 1
  4. 2026HoverAI: An Embodied Aerial Agent for Natural Human-Drone Interactioncited by 0
  5. 2026DiffusionCinema: Text-to-Aerial Cinematographycited by 0
  6. 2026PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVscited by 0
  7. 2026Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Reviewcited by 0
  8. 2026RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigationcited by 0
  9. 2026Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searchingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
  2. 2026AeroGround: A Comprehensive Benchmark for Aerial-Ground Collaborative Reasoning
  3. 2025RaceVLA: VLA-based Racing Drone Navigation with Human-like Behaviour
  4. 2025UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios
  5. 2026WareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart Warehouses
  6. 2026Knowing the Self, Understanding the World: A Dual-Cognition Benchmark for UAV Spatio-temporal Reasoning with MLLMs
  7. 2025VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments
  8. 2026VLN-Pilot: Large Vision-Language Model as an Autonomous Indoor Drone Operator