MEKAWIRE
South KoreaSubsidiary

NAVER LABS

NAVER's research subsidiary for robotics, physical AI, spatial intelligence and digital twins.

Website
  • Sep 4, 2026
    NAVER LABS turns robot service logic into drag-and-drop cards with FLOW, already running in a Saudi smart building

    NAVER LABS said in a company blog post on Sept 4 that FLOW, a tool in its ARC brain robot platform, lets building operators define how a robot service runs by arranging cards such as "order received", "move robot" and "pickup confirmed" and linking them with conditions, instead of having developers write the logic in code. Each card maps to an executable function such as driving to a location, opening a storage drawer, changing a status or sending a notification. The company said the business logic of robot services in a smart building in Saudi Arabia was built on FLOW and connected to ARC brain, that its Yaesu robot building project in Tokyo is being moved to the same structure, and that the next step is letting natural-language AI agents draft flows for a human to review, with FLOW serving as the readable layer for checking and debugging agent decisions. NAVER LABS gave no release date or pricing for outside customers. This is the first NAVER LABS story in MEKAWIRE's database, which lists the unit as NAVER's research subsidiary for robotics, physical AI, spatial intelligence and digital twins.

    Subject
  • Sep 1, 2026
    NAVER LABS takes DUSt3R successor BLASt3R and two other spatial-AI papers to ECCV 2026, one picked as a spotlight

    NAVER LABS said in a blog post on Sept 1 that three of its spatial-intelligence papers were accepted at ECCV 2026, the European computer-vision conference. NAVER LABS Europe presented BLASt3R (Bundle Adjustment of Any Image Set with Multi-view Matching and Monocular Priors), a follow-up to its DUSt3R 3D-vision model that reconstructs a scene from the relationships between many images; the lab says it is markedly faster and more accurate than earlier models and folds in SLAM, so a moving robot can estimate its own position and map its surroundings on the device rather than relying on a server. A second paper, Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints, uses a vision-language model to label objects, including ones never seen in training, and writes them into a real-time bird's-eye-view map for vehicles and robots. The third, InSpace, rebuilds a room's walls, floor and furniture in 3D from a single 360-degree panorama and was selected as an ECCV spotlight, a slot the lab says goes to about 1 to 2% of submissions. The lab did not give benchmark numbers in the post. On MEKAWIRE's pages this is the research layer under NAVER LABS' commercial robot stack: three days later it unveiled FLOW, a no-code tool for authoring services on its ARC brain robot platform, which already runs in its 1784 headquarters and is being deployed in Saudi Arabia and Tokyo's Yaesu.

    Subject