NeRFoot: 画像ベース視覚サーボのためのロボットフットプリント推定
NeRFoot: Robot-Footprint Estimation for Image-Based Visual Servoing
NeRFを3D表現の事前情報として使い、ロボットの外観画像からCNNでフットプリントを推定し、画像ベース視覚サーボの動作領域を広げる手法を提案。
著者: Daoxin Zhong, Luke Robinson, Daniele De Martini
分類: cs.RO
原文アブストラクト
This paper investigates the utility of Neural Radiance Fields (NeRF) models in extending the regions of operation of a mobile robot, controlled by Image-Based Visual Servoing (IBVS) via static CCTV cameras. Using NeRF as a 3D-representation prior, the robot's footprint may be extrapolated geometrically and used to train a CNN-based network to extract it online from the robot's appearance alone. The resulting footprint results in a tighter bound than a robot-wide bounding box, allowing the robot's controller to prescribe more optimal trajectories and expand its safe operational floor area.
