aerial-robotics

论文提出轨迹接地指令翻译器（TGIT），在冻结的空中VLN导航器前端将简短的用户意图指令翻译为可执行命令，解决训练指令与部署指令之间的"指令差距"，将真实人类指令上的成功率从11.33%提升至32.51%。

MissionBench is a new benchmark for evaluating multimodal large language models (MLLMs) on long-horizon embodied tasks in aerial 3D environments, revealing that even the best models succeed on fewer than 35% of missions compared to 84.4% human performance.