Get Started
Research questionHow can service robots map and retrieve objects under occlusion and restricted access without disturbing known shelf regions?Occlusion and limited reach make shelf contents difficult to understand and access. Actions that reveal or retrieve objects can also disturb regions that are already mapped with confidence.
Computer Vision
Machine Learning
Robotics
Latest papersRecent research connected to this question, newest first.MS-MEM: Multi-Skill Manipulation-Enhanced Mapping via Uncertainty- and Disturbance-Aware Action SelectionThe source concerns an evidential mapping framework for service robots that considers viewpoint selection, pushing, and grasping, including uncertainty in scene beliefs and grasp affordances and orientations. Its evidence comes from experiments comparing combined actions with single-skill and disturbance-unconstrained baselines; the reported setting is cluttered shelf manipulation.research paper · Sep 2, 2026
Related questions
How can dual-arm robots recover occluded object surfaces from calibrated, synchronized multi-view observations?How can robots maintain geometrically grounded semantic maps as objects and spatial relations change in real time?How can semantic occupancy systems detect unknown objects under distribution shift in autonomous-driving scenes?How can warehouse robots estimate 9D box pose from one RGB-D view under clutter and occlusion without per-object CAD models?
Home
Topics
Search
Library