Anthropomorphic Grasping with Neural Object Shape Completion

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung

Beitragende

  • Diego Hidalgo-Carvajal - , Technische Universität München, Technische Universität Dresden (Autor:in)
  • Hanzhi Chen - , Technische Universität München (Autor:in)
  • Gemma C. Bettelani - , Technische Universität München (Autor:in)
  • Jaesug Jung - , Technische Universität München (Autor:in)
  • Melissa Zavaglia - , Technische Universität München (Autor:in)
  • Laura Busse - , Ludwig-Maximilians-Universität München (LMU) (Autor:in)
  • Abdeldjallil Naceri - , Technische Universität München (Autor:in)
  • Stefan Leutenegger - , Technische Universität München (Autor:in)
  • Sami Haddadin - , Technische Universität München, Technische Universität Dresden (Autor:in)

Abstract

The progressive prevalence of robots in human-suited environments has given rise to a myriad of object manipulation techniques, in which dexterity plays a paramount role. It is well-established that humans exhibit extraordinary dexterity when handling objects. Such dexterity seems to derive from a robust understanding of object properties (such as weight, size, and shape), as well as a remarkable capacity to interact with them. Hand postures commonly demonstrate the influence of specific regions on objects that need to be grasped, especially when objects are partially visible. In this work, we leverage human-like object understanding by reconstructing and completing their full geometry from partial observations, and manipulating them using a 7-DoF anthropomorphic robot hand. Our approach has significantly improved the grasping success rates of baselines with only partial reconstruction by nearly 30% and achieved over 150 successful grasps with three different object categories. This demonstrates our approach's consistent ability to predict and execute grasping postures based on the completed object shapes from various directions and positions in real-world scenarios. Our work opens up new possibilities for enhancing robotic applications that require precise grasping and manipulation skills of real-world reconstructed objects.

Details

OriginalspracheEnglisch
Seiten (von - bis)8034-8041
Seitenumfang8
FachzeitschriftIEEE Robotics and Automation Letters
Jahrgang8
Ausgabenummer12
PublikationsstatusVeröffentlicht - 1 Dez. 2023
Peer-Review-StatusJa