Fly as Instructed: Refining World-Action Policies for UAV Vision-Language Navigation

Natural language-guided UAV navigation enables intuitive human-robot interaction and flexible autonomous flight in complex environments. However, reliable navigation requires accurate instruction following, continuous task progress tracking, and safe obstacle avoidance, which remain challenging for existing world-action models that primarily focus on action prediction. To address these limitations, we propose a world-action learning framework that integrates three complementary mechanisms: a language-conditioned action interface with targeted post-training for instruction-responsive motion, recurrent instruction-consumption prediction to track task progress and determine termination, and Gaussian-scene post-training to enhance obstacle avoidance through trajectory imitation and differentiable geometric feedback. Closed-loop evaluations and ablation studies demonstrate improvements in sequential task completion, safe goal reaching, and timely termination. Furthermore, direct one-step denoising reduces inference overhead, and real-world indoor and outdoor flights validate the framework's effectiveness.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-17
DOI
https://doi.org/10.48550/arxiv.2611.22883
Primary Topic
Reinforcement Learning in Robotics
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Fly as Instructed: Refining World-Action Policies for UAV Vision-Language Navigation

Zijun Zhou, Yanke Sun, Jie Mei, Youmin Gong et al.
arXiv (Cornell University)
Reinforcement Learning in Robotics
preprint

Fly as Instructed: Refining World-Action Policies for UAV Vision-Language Navigation

Zijun Zhou, Yanke Sun, Jie Mei, Youmin Gong, Yuhan Zong
preprint en

Abstract

Natural language-guided UAV navigation enables intuitive human-robot interaction and flexible autonomous flight in complex environments. However, reliable navigation requires accurate instruction following, continuous task progress tracking, and safe obstacle avoidance, which remain challenging for existing world-action models that primarily focus on action prediction. To address these limitations, we propose a world-action learning framework that integrates three complementary mechanisms: a language-conditioned action interface with targeted post-training for instruction-responsive motion, recurrent instruction-consumption prediction to track task progress and determine termination, and Gaussian-scene post-training to enhance obstacle avoidance through trajectory imitation and differentiable geometric feedback. Closed-loop evaluations and ablation studies demonstrate improvements in sequential task completion, safe goal reaching, and timely termination. Furthermore, direct one-step denoising reduces inference overhead, and real-world indoor and outdoor flights validate the framework's effectiveness.

arXiv (Cornell University)
Reinforcement Learning in Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon