FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback

arxiv(2023)

引用 2|浏览30
暂无评分
摘要
In this paper, we address the problem of using visuo-tactile feedback for 6-DoF localization and 3D reconstruction of unknown in-hand objects. We propose FingerSLAM, a closed-loop factor graph-based pose estimator that combines local tactile sensing at finger-tip and global vision sensing from a wrist-mount camera. FingerSLAM is constructed with two constituent pose estimators: a multi-pass refined tactile-based pose estimator that captures movements from detailed local textures, and a single-pass vision-based pose estimator that predicts from a global view of the object. We also design a loop closure mechanism that actively matches current vision and tactile images to previously stored key-frames to reduce accumulated error. FingerSLAM incorporates the two sensing modalities of tactile and vision, as well as the loop closure mechanism with a factor graph-based optimization framework. Such a framework produces an optimized pose estimation solution that is more accurate than the standalone estimators. The estimated poses are then used to reconstruct the shape of the unknown object incrementally by stitching the local point clouds recovered from tactile images. We train our system on real-world data collected with 20 objects. We demonstrate reliable visuo-tactile pose estimation and shape reconstruction through quantitative and qualitative real-world evaluations on 6 objects that are unseen during training.
更多
查看译文
关键词
6-DoF localization,closed-loop factor graph-based,closed-loop unknown object,constituent pose estimators,current vision,detailed local textures,estimated poses,factor graph-based optimization framework,FingerSLAM,global vision sensing,in-hand objects,local point clouds,local tactile,loop closure mechanism,multipass refined tactile-based,optimized pose estimation solution,sensing modalities,standalone estimators,tactile images,vision-based pose estimator,visuo-tactile feedback,wrist-mount camera
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要