CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking

• URL: http://arxiv.org/abs/2607.15004v1
• Date: Thu, 16 Jul 2026 13:52:08 GMT
• Title: CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking
• Abstract summary: Vision-Language-Action (VLA) policies can track visible targets effectively, but their performance often degrades when buildings, vegetation, or roadside objects block the line of sight.<n>We present CosFly-VLA, a spatially aware VLA model that jointly grounds the target, estimates its visibility, and generates continuous flight actions.<n>Relative to OpenVLA, CosFly-VLA-0.8B reduces open-loop Average Displacement Error (ADE) by 34.1% on seen-test and 35.3% on unseen-test.
• Score: 6.465600276213322
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic target tracking is essential for Unmanned Aerial Vehicles (UAVs) operating in complex urban environments, where both the target and the camera viewpoint change continuously. Existing Vision-Language-Action (VLA) policies can track visible targets effectively, but their performance often degrades when buildings, vegetation, or roadside objects block the line of sight. During sustained occlusion, a policy may lose the target state, execute actions toward an incorrect region, and amplify this error through subsequent observations until re-acquisition becomes impossible. To this end, we present CosFly-VLA, a spatially aware VLA model that jointly grounds the target, estimates its visibility, and generates continuous flight actions through a structured prediction interface. To train this policy, we use a large-scale recipe over diverse data sources. Spatially Grounded Continued Pretraining (CPT) on a 500k mixed pool injects UAV-view depth, distance, and 3-D spatial reasoning. A three-stage Curriculum-based Supervised Fine-Tuning (SFT) process then specializes the tracker through multi-head warm-up followed by two-stage curriculum learning over natural and hard / long-occlusion data. Chain-of-Thought (CoT) training subsequently teaches recovery-oriented reasoning traces before structured answers. Finally, a closed-loop Reinforcement Learning (RL) stage optimizes tracking behavior with a multi-component reward covering stand-off tracking, grounding quality, collision avoidance, and task success. Relative to OpenVLA, CosFly-VLA-0.8B reduces open-loop Average Displacement Error (ADE) by 34.1% on seen-test and 35.3% on unseen-test. Closed-loop optimization improves Success Rate (SR) by 29.8% and 2.5%, respectively. These results demonstrate progress from visible-frame imitation toward spatially grounded action-closed-loop control, evaluated under a shared oracle state history.

Related papers

• On-Policy Self-Distillation in Diffusion Models [89.32656931795293]
  Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change.<n>We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries.<n>Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators.
  arXiv  Detail & Related papers  (2026-08-25T14:55:24Z)
• RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation [16.942230083606674]
  Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable flight actions.<n>We propose RecoverFly, a failure-aware RL post-training framework for end-to-end UAV-VLA policies.
  arXiv  Detail & Related papers  (2026-08-10T11:37:46Z)
• VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training [52.05483137072975]
  Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation.<n>We present VISTA, a framework that bridges this dual gap through three synergistic components.<n>We release the physical-validation pipeline, UMI-VQA, validated trajectory data, and the pre-trained model for the community.
  arXiv  Detail & Related papers  (2026-06-03T10:38:45Z)
• Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts [18.44683570310399]
  Low-quality actions may cause physical failures during execution or lead to misleading world-model rollouts with redundant rendering costs.<n>We propose Pre-VLA, a unified runtime verification architecture that performs preemptive action assessment validity before physical execution or world-model imagination.
  arXiv  Detail & Related papers  (2026-05-21T13:13:31Z)
• Instance-level Visual Active Tracking with Occlusion-Aware Planning [61.982298426203165]
  Visual Active Tracking (VAT) aims to control cameras to follow a target in 3D space.<n>VAT faces two key bottlenecks in real-world deployment: confusion from visually similar distractors and severe failure under occlusions.<n>We propose OA-VAT, a unified pipeline with three complementary modules.
  arXiv  Detail & Related papers  (2026-04-23T09:11:50Z)
• Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures [14.313346858887286]
  Vision-Language-Action (VLA) models for autonomous driving often hit a performance plateau during Reinforcement Learning (RL) optimization.<n>This stagnation arises from exploration capabilities constrained by previous Supervised Fine-Tuning (SFT)<n>We propose Explicit Learning from Failures (ELF-VLA), a framework that augments RL with structured diagnostic feedback.
  arXiv  Detail & Related papers  (2026-03-01T11:41:22Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation [95.89924101984566]
  We introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM)<n>GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories.<n>LCM injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory.
  arXiv  Detail & Related papers  (2026-02-22T15:39:34Z)
• Eva-Tracker: ESDF-update-free, Visibility-aware Planning with Target Reacquisition for Robust Aerial Tracking [51.06229328990625]
  Eva-Tracker is a visibility-aware trajectory planning framework for aerial tracking.<n>It eliminates ESDF updates and incorporates a recovery-capable path generation method for target reacquisition.<n>Our approach delivers more robust tracking results with lower computational effort than existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-13T02:56:34Z)
• KEPT: Knowledge-Enhanced Prediction of Trajectories from Consecutive Driving Frames with Vision-Language Models [19.625631486595505]
  This paper introduces KEPT, a knowledge-enhanced vision-language framework.<n>It predicts ego trajectories directly from consecutive front-view driving frames.<n>It achieves state-of-the-art performance across open-loop protocols.
  arXiv  Detail & Related papers  (2025-09-03T03:10:42Z)
• A Vision Based Deep Reinforcement Learning Algorithm for UAV Obstacle Avoidance [1.2693545159861856]
  We present two techniques for improving exploration for UAV obstacle avoidance. The first is a convergence-based approach that uses convergence error to iterate through unexplored actions and temporal threshold to balance exploration and exploitation. The second is a guidance-based approach which uses a Gaussian mixture distribution to compare previously seen states to a predicted next state in order to select the next action.
  arXiv  Detail & Related papers  (2021-03-11T01:15:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.