X-Fly is a staged training framework designed to improve full‑chunk aerial vision‑language navigation. It uses Recovery DAgger to label learner‑visited states with smooth action chunks and a STOP command, and Flow‑GRPO to jointly refine a chunked flow controller and a Bernoulli STOP policy. The approach achieves 74.18% success rate on test‑seen and 51.73% on test‑unseen, outperforming baseline methods.
Aerial vision-language navigation (VLN) agents built on large vision-language models are expensive to query. Executing a complete predicted action chunk before replanning amortizes this cost, reducing...
arXiv:2608. 09467v1 Announce Type: cross Abstract: Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable flight actions in complex environments.
arXiv:2608. 12308v1 Announce Type: cross Abstract: Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it has reached a navigation goal under partial observability.
Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable flight actions in complex environments. Although recent end-to-end UAV vision-language-action (UAV-VLA) policies reduce reliance on separately designed perception, planning, and control modules, their behavior-cloning objectives provide limited corrective supervision for interactive closed-loop execution.
The paper introduces VLN on the Fly, an onboard vision‑language navigation stack for aerial robots that separates grounding, planning, and control into inspectable stages. A quantized vision‑language model grounds instructions to a coarse image cell, depth estimation lifts this to a 3D goal, a fast B‑spline planner generates a feasible trajectory, and a pretrained reinforcement learning policy translates the trajectory into motor commands. In controlled indoor flights, the stack achieved the target in 13 of 15 trials with a mean goal error of 5.72 cm and 39.3% GPU utilization, and successfully tracked collision‑free trajectories in cluttered environments.
arXiv:2606. 28397v1 Announce Type: cross Abstract: Vision-language navigation (VLN) has recently advanced with large language and multimodal models, enabling agents to follow natural-language instructions in unseen environments without training a task-specific navigation policy.
arXiv:2606. 31846v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control.
arXiv:2608. 02958v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies trained by behavior cloning fail silently: from the action stream alone, a collapsing rollout looks much like one making clean progress, because imitation supplies no notion of progress.
arXiv:2609.21216v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies based on flow matching generate action chunks through repeated evaluations of an action expert. Increasing the...
arXiv:2609.22854v1 Announce Type: cross Abstract: Vision-language-action models often predict actions from only the current observation, which can leave tasks involving object occlusion or visually i...
Rewind-IL is a training‑free online safeguard for generative action‑chunked imitation learning policies. It uses a zero‑shot failure detector based on Temporal Inter‑chunk Discrepancy Estimate (TIDE) and a state‑respawning mechanism that returns the robot to a verified safe intermediate state. The system builds a checkpoint library offline with a vision‑language model and monitors self‑consistency online, rewinding execution to the latest safe checkpoint when a failure is detected, thereby improving reliability in long‑horizon manipulation tasks.
arXiv:2607. 29235v1 Announce Type: cross Abstract: Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands repeated re-grounding in real observations--not recursive rollout.