Tag: computer-vision
All the articles with the tag "computer-vision".
-
Navigating Blind: How Drones Fly Without GPS — and Why It Matters More Than Ever
GPS jamming and spoofing are now routine in contested airspace, and indoor/underground operations have always lived without it. This post is a technical survey of GPS-denied drone navigation in 2026 — VIO, visual SLAM, terrain-relative navigation, satellite image matching, magnetic anomaly navigation (MagNav), LiDAR SLAM, and multi-modal factor-graph fusion. Deep dives into satellite image matching (the most promising daytime approach) and MagNav (the dark horse that works at night, in fog, and is unjammable). With lessons from Ukraine, the open problems, and a practical stack for builders.
-
The Perception–Planning Gap: What's Actually Hard About Visual AI in 2026
A technical survey of where visual perception and planning research actually stands in 2026. Pixel-level perception is largely solved at the representation layer, but perception-for-action — geometry, physics, dexterity, long-horizon control — is not. Reading the recent literature on JEPA, DreamerV3, Sora-as-world-model, RT-2 / OpenVLA / π0, Helix, Gemini Robotics, DUSt3R / MASt3R / VGGT, and the world-model evaluation papers (WorldModelBench, Physion, IntPhys 2), the through-line is the same: we have strong representations and architectural ideas, but the data, evaluation, and physical-grounding infrastructure to validate them is what's missing.