DroneWAM: Efficient World Action Model for Drone Visual Navigation

arXiv:2609.33148 · cs.CV · Submitted 2026-09-27 · Read on arXiv

cs.CV

Submitted: 2026-09-27

Updated: 2026-09-27

Terminology

• Accuracy — 22× in this paper · explained in 1 episode
• World Model — 19× in this paper · explained in 7 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Absolute Trajectory Error — 3× in this paper
• Calibration — 3× in this paper · explained in 7 episodes
• Relative Pose Error — 3× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 2× in this paper
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Consistency — 2× in this paper · explained in 3 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Dynamics — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Predictive Modeling — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-Supervised Learning — 1× in this paper · explained in 7 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation
• Policy-Guided World Model Planning for Language-Conditioned Visual Navigation
• Planning with Reasoning using Vision Language World Model
• Action100M: A Large-scale Video Action Dataset
• World Models
• Dream to Control: Learning Behaviors by Latent Imagination
• The DAWN of World-Action Interactive Models
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
• ViNT: A Foundation Model for Visual Navigation
• World Action Models: A Survey
• Co-Evolving Latent Action World Models
• WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
• World Action Models are Zero-shot Policies
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space
• World Action Planner: Generalizable Robot Decision-Making with Action-Conditioned World Models
• WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models