LesenForschungRadarAnlageframework
Anmelden / Registrieren
← Zurück zur Lektüre
NewsThema · DroneCATS基准Wesentlich1 Min. LesezeitDisconfirmAI Redaktion

NAVER Releases DroneCATS: Small Models Navigate Well But Fail to Terminate; Fine-Tuned 2B Model Outperforms Frontier Models in Real Flight

DroneCATS reveals that MLLM failures in drone control stem from incorrect 'arrival declaration' rather than navigation, with a fine-tuned 2B model surpassing frontier models in real-world tests.

2026-10-16 12:00 GMT+8

The DroneCATS benchmark released by NAVER Cloud's Drone AI Team indicates that the primary bottleneck for Multimodal Large Language Models (MLLMs) acting as generalist vision-language-action agents for drone control is not spatial perception or navigation, but the discipline of executing terminating actions.

Evaluating ten MLLMs ranging from frontier models to small open models, the study found that small open models often navigate into the success radius more reliably than frontier models but lose episodes by declaring arrival prematurely or not at all. In contrast, frontier models achieve higher success rates but suffer from latency issues that cause them to lose moving targets.

Guided by this failure analysis, the team fine-tuned a 2B parameter model on drone action data. Its success rate rose from 0% to 31% in simulation, and it outperformed frontier models in real drone flight tests.

Quellen

  • arxiv.org↗
Thema

DroneCATS基准

NAVER Cloud发布DroneCATS基准,评估多模态大语言模型(MLLM)作为无人机控制代理的能力。研究发现,小型开源模型在导航精度上往往优于前沿模型,但因无法正确执行“到达声明”协议而导致任务失败;而前沿模型虽能识别目标,却因延迟…

Anmelden / Registrieren
LesenForschungRadarAnlageframework

4 Schritte1 BeiträgeAktualisiert 2026-10-17 13:42

Wie es dazu kam

  1. 2026-09-01论文v1提交至arXiv,提出DroneCATS-Agent架构,将MLLM直接置入无人机控制回路,仅通过提示词定义动作空间。arxiv.org ↗
  2. 2026-09-02Hugging Face社区讨论指出,Qwen3.5-9B等小模型虽能进入成功半径,但常因过早或从不声明到达而输掉回合。huggingface.co ↗
  3. 2026-10-15论文v2更新,扩展至多无人机编队指挥场景,发现所有零样本模型作为指挥官控制子代理时表现均优于直接驾驶所有无人机。arxiv.org ↗

Was noch ungeklärt ist

  • DroneCATS基准代码和数据集的具体发布时间尚未确定。
  • 微调2B模型在更复杂真实环境中的鲁棒性有待验证。
Vollständiges Thema lesen →
Recherche fortsetzen →