Get Started
Research questionHow can dual-arm robots recover occluded object surfaces from calibrated, synchronized multi-view observations?A single camera view leaves parts of an object hidden and produces incomplete surface geometry. Combining observations from multiple robot-mounted viewpoints requires consistent sensor calibration, synchronization, and camera-pose recovery.
Computer Vision
Robotics
Latest papersRecent research connected to this question, newest first.DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic PerceptionApplies to two independently moving eye-in-hand sensors recording RGB, depth, and stereo infrared data alongside synchronized robot joint states. The evidence covers ten tabletop objects and evaluates deterministic fusion into partial point clouds and measured surface meshes; it does not assess learned or generative surface completion.research paper · Sep 2, 2026
Related questions
How can systems recover individually editable meshes for hundreds of objects from limited, heavily occluded views?How can robotic manipulation policies combine vision, language, and touch for reliable contact-rich tasks under occlusion?How can continuum robots jointly reconstruct their shape and estimate multiple contact forces at unknown locations?How can dual-arm vision-language-action policies avoid self-collisions with grasped objects?
Home
Topics
Search
Library