CognitiveDrone：一個用於無人機即時認知任務解決與推理的VLA模型及評估基準

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

March 3, 2025

作者: Artem Lykov, Valerii Serpiva, Muhammad Haris Khan, Oleg Sautenkov, Artyom Myshlyaev, Grik Tadevosyan, Yasheerah Yaqoot, Dzmitry Tsetserukou

cs.AI

摘要

本文介紹了CognitiveDrone，這是一種專為需要高級認知能力的複雜無人機（UAV）任務量身定制的新型視覺-語言-動作（VLA）模型。該模型基於包含超過8,000條模擬飛行軌跡的數據集進行訓練，涵蓋三個關鍵類別——人類識別、符號理解與推理——並根據第一人稱視覺輸入和文本指令生成實時4D動作命令。為進一步提升在複雜場景中的表現，我們提出了CognitiveDrone-R1，該版本整合了額外的視覺-語言模型（VLM）推理模塊，以在高頻控制前簡化任務指令。使用我們開源的基準測試CognitiveDroneBench進行的實驗評估顯示，儘管以競速為導向的模型（RaceVLA）的總體成功率為31.3%，但基礎版CognitiveDrone模型達到了59.6%，而CognitiveDrone-R1則實現了77.2%的成功率。這些結果表明，在關鍵認知任務中，性能提升高達30%，突顯了將高級推理能力融入無人機控制系統的有效性。我們的貢獻包括開發了一種用於無人機控制的先進VLA模型，並引入了首個專門用於評估無人機操作中認知任務的基準測試。完整資源庫可在cognitivedrone.github.io獲取。

English

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