AcTExplore: Active Tactile Exploration of Unknown Objects

Autor:	Shahidzadeh, Amir-Hossein, Yoo, Seong Jong, Mantripragada, Pavan, Singh, Chahat Deep, Fermüller, Cornelia, Aloimonos, Yiannis
Rok vydání:	2023
Předmět:	Computer Science - Robotics Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Tactile exploration plays a crucial role in understanding object structures for fundamental robotics tasks such as grasping and manipulation. However, efficiently exploring such objects using tactile sensors is challenging, primarily due to the large-scale unknown environments and limited sensing coverage of these sensors. To this end, we present AcTExplore, an active tactile exploration method driven by reinforcement learning for object reconstruction at scales that automatically explores the object surfaces in a limited number of steps. Through sufficient exploration, our algorithm incrementally collects tactile data and reconstructs 3D shapes of the objects as well, which can serve as a representation for higher-level downstream tasks. Our method achieves an average of 95.97% IoU coverage on unseen YCB objects while just being trained on primitive shapes. Project Webpage: https://prg.cs.umd.edu/AcTExplore Comment: 8 pages, 6 figures, Accepted to ICRA 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2310.08745 Zobrazit plný text záznamu View this record from Arxiv