Phy-Tac: Toward Human-Like Grasping via Physics-Conditioned Tactile Goals

TL;DR

This paper introduces Phy-Tac, a physics-inspired tactile method for robotic grasping that optimizes force, predicts tactile feedback, and adapts to object geometry, achieving more human-like and stable grasps.

Contribution

The paper presents a novel physics-conditioned tactile approach combining pose selection, tactile prediction, and force regulation for stable, force-efficient robotic grasping.

Findings

Phy-LDM achieves high tactile prediction accuracy.

Phy-Tac outperforms baselines in grasp stability.

Demonstrates adaptive, force-efficient manipulation on robots.

Abstract

Humans naturally grasp objects with minimal level required force for stability, whereas robots often rely on rigid, over-squeezing control. To narrow this gap, we propose a human-inspired physics-conditioned tactile method (Phy-Tac) for force-optimal stable grasping (FOSG) that unifies pose selection, tactile prediction, and force regulation. A physics-based pose selector first identifies feasible contact regions with optimal force distribution based on surface geometry. Then, a physics-conditioned latent diffusion model (Phy-LDM) predicts the tactile imprint under FOSG target. Last, a latent-space LQR controller drives the gripper toward this tactile imprint with minimal actuation, preventing unnecessary compression. Trained on a physics-conditioned tactile dataset covering diverse objects and contact conditions, the proposed Phy-LDM achieves superior tactile prediction accuracy, while the Phy-Tac outperforms fixed-force and GraspNet-based baselines in grasp stability and force efficiency. Experiments on classical robotic platforms demonstrate force-efficient and adaptive manipulation that bridges the gap between robotic and human grasping.