Predicting Grasping Compliance in Robotic Hands through Analytical-Model-Informed Neural Networks
2026-07-20 • Robotics
Robotics
AI summaryⓘ
The authors look at how robot hands hold and use tools when applying force, not just whether the object is simply held or dropped. They point out that the flexibility (compliance) of the hand and tool affects how they respond to pushing or pulling, which is complex to predict, especially in simpler robot hands with few motors. To solve this, they create a new model that mixes physics rules with computer learning to better guess how the hand and tool will move and stay stable under pressure. Their model works well on a robot hand with three fingers and predicts outcomes better than a typical machine learning method while staying true to physical laws.
robotic manipulationgrasp complianceunderactuated handsforceful tool useanalytical modelneural networkgrasp stabilityphysical consistencyhybrid predictive model
Authors
Qianwen Zhao, Long Wang
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.