Paul B. Umbanhowar — accepted AI-conference papers

2021

Visiflex: A Low-Cost Compliant Tactile Fingertip for Force, Torque, and Contact Sensing

Alfonso J. Fernandez, Huan Weng, Paul B. Umbanhowar, Kevin M. Lynch

RA-L 2021

We present the Visiflex, an inexpensive compliant tactile fingertip capable of contact localization and 6 degree-of-freedom (dof) contact force and torque measurement. Because manipulation of rigid or nearly-rigid objects requires compliance at the contact, we build compliance directly into the Visi

Cited by 20 Source ↗Scholar ↗

2020

The Soft-Landing Problem: Minimizing Energy Loss by a Legged Robot Impacting Yielding Terrain

Daniel J. Lynch, Kevin M. Lynch, Paul B. Umbanhowar

RA-L 2020

Enabling robots to walk and run on yielding terrain is vital to endeavors ranging from disaster response to extraterrestrial exploration. While dynamic legged locomotion on rigid ground is challenging enough, yielding terrain presents additional challenges such as ground deformation which dissipates

Cited by 22 Source ↗Scholar ↗