Get Started
Research questionHow can robots maintain geometrically grounded semantic maps as objects and spatial relations change in real time?A robot must reconcile geometric estimates, detected objects, persistent identities, and structured relations as new observations arrive. Scene changes and estimation errors can leave object instances or spatial relationships inconsistent with the map.
Computer Vision
Image & Video Processing
Robotics
Latest papersRecent research connected to this question, newest first.A hybrid pipeline for dynamic ontology-based semantic mappingThe source describes a pipeline using an external calibrated camera with homography-based geometric mapping, object detection and tracking, ontology-driven updates, and linear-regression correction of real-world coordinates. It supplies a system description but no performance results or evidence beyond the stated real-time mapping setup.research paper · Sep 3, 2026
Related questions
How can robotic agents maintain queryable spatial-semantic memory for precise, low-latency answers in complex environments?How can mobile robots understand people and surroundings well enough to navigate safely and collaborate adaptively?How can long-horizon indoor mobile manipulators track embodiment state and repair plans without dense scene maps?How can domestic robots export task-useful perception without leaking household semantics, geometry, or goals?
Home
Topics
Search
Library