Tracing Energy Flow: Learning Tactile-based Grasping Force Control to Reduce Slippage in Dynamic Object Interaction

Cheng-Yu Kuo, Hirofumi Shin, Takamitsu Matsubara

Keywords: Model Learning for Control, Perception for Grasping and Manipulation, Grasping

TL;DR: The full paper is accepted by IEEE RA-L and will present at ICRA 2026.

Abstract:

Regulating grasping force to reduce slippage during
dynamic object interaction remains a fundamental challenge in
robotic manipulation, especially when objects are manipulated by
multiple rolling contacts, have unknown properties, and when
external sensing is unreliable. We propose a physics-informed
energy abstraction that models the object as a virtual energy
container. The inconsistency between the fingers’ applied power
and the object’s retained energy provides a physically grounded
signal for inferring slip-aware stability. Building on this abstrac-
tion, we employ model-based learning and planning to efficiently
model energy dynamics from tactile sensing and perform real-
time grasping force optimization. Experiments in both simulation
and hardware demonstrate that our method can learn grasping
force control from scratch within minutes, effectively reduce
slippage, and extend grasp duration across diverse motion-object
pairs, all without relying on external sensing or prior object
knowledge.

Submission Number: 14