STAIR: Semantic-Targeted Active Implicit Reconstruction

arXiv:2403.11233v1 Announce Type: cross
Abstract: Many autonomous robotic applications require object-level understanding when deployed. Actively reconstructing objects of interest, i.e. objects with specific semantic meanings, is therefore relevant for a robot to perform downstream tasks in an initially unknown environment. In this work, we propose a novel framework for semantic-targeted active reconstruction using posed RGB-D measurements and 2D semantic labels as input. The key components of our framework are a semantic implicit neural representation and a compatible planning utility function …

abstract applications arxiv autonomous cs.cv cs.ro environment framework novel object objects rgb-d robot robotic semantic tasks type understanding work