Predicting Grasping Compliance in Robotic Hands through Analytical-Model-Informed Neural Networks

2026-07-20

AI Summary

Traditional grasp modeling often reduces grasping to a binary success/failure problem, failing to capture the nonlinear deformations and force interactions arising from the compliance of underactuated hands during power-tool manipulation. This work proposes a hybrid predictive model, AMINN, that uniquely integrates analytical mechanics with data-driven learning by embedding an analytical mechanics layer within a neural network. By incorporating the kinematics and contact mechanics of multi-fingered underactuated hands, AMINN enables physically interpretable predictions of grasp stability and intra-hand displacements under load. Experimental results demonstrate that the method significantly outperforms black-box multilayer perceptrons across diverse loading conditions, achieving high prediction accuracy while notably enhancing physical consistency—such as energy conservation—and mechanical interpretability of the outputs.

Abstract

In robotic manipulation studies, grasping is often treated as a binary success or failure problem, usually defined by whether the object simply stays in the hand. For forceful tool use, however, this view is insufficient because grasp compliance becomes a critical factor governing how the hand and tool behave under load. Compliance arises from coupled kinematics, grasp configuration, passive mechanics, and contact conditions, producing nonlinear behavior in which deformation and interaction forces influence each other. Understanding this relationship is essential for predictive models of how a grasped tool and a compliant hand jointly respond to external loading. In underactuated hands, these effects are amplified: such designs offer low cost and adaptive grasping, but make compliance behavior more difficult to model and predict. Our goal is therefore to develop a predictive model for grasped tool behavior during forceful interactions. To address this challenge, we introduce an analytical model informed neural network (AMINN), a hybrid predictive model that combines an analytical mechanics layer with data driven learning to estimate grasp stability and in hand tool displacement under external loading. The model is evaluated on a three finger underactuated robotic hand and shows strong predictive capability with mechanically meaningful outputs across diverse loading conditions. Compared with a black box multilayer perceptron baseline, AMINN also achieves better energy based physical consistency. Beyond prediction accuracy alone, this framework advances physically interpretable learning for robotic manipulation and supports more reliable, safer, and more trustworthy autonomous tool use in safety critical settings during forceful interaction.

Problem

• grasping compliance
• robotic manipulation
• underactuated hands
• forceful tool use
• predictive modeling

Innovation

• compliant grasping
• analytical-model-informed neural network
• underactuated robotic hand
• physical consistency
• tool use prediction