Tactile Recognition of Both Shapes and Materials with Automatic Feature Optimization-Enabled Meta Learning

2026-03-09

AI Summary

This work addresses the challenge of shape and material recognition in robotic tactile perception, where data scarcity and high acquisition costs hinder performance. To overcome this, the authors propose the AFOP-ML framework, which integrates an automated feature space optimization mechanism into prototypical networks to enable few-shot meta-learning from four-channel tactile signals. Evaluated on a 36-class benchmark, the method achieves 96.08% accuracy in the 5-way 1-shot setting and maintains strong performance at 88.7% even under the extreme 36-way 1-shot scenario. Furthermore, it demonstrates robust generalization to unseen shapes, materials, and perturbations in force and sliding velocity, offering novel insights for tactile perception and sensor design.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning with Manifolds
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Tactile perception is indispensable for robots to implement various manipulations dexterously, especially in contact-rich scenarios. However, alongside the development of deep learning techniques, it meanwhile suffers from training data scarcity and a time-consuming learning process in practical applications since the collection of a large amount of tactile data is costly and sometimes even impossible. Hence, we propose an automatic feature optimization-enabled prototypical network to realize meta-learning, i.e., AFOP-ML framework. As a ``learn to learn"network, it not only adapts to new unseen classes rapidly with few-shot, but also learns how to determine the optimal feature space automatically. Based on the four-channel signals acquired from a tactile finger, both shapes and materials are recognized. On a 36-category benchmark, it outperforms several existing approaches by attaining an accuracy of 96.08% in 5-way-1-shot scenario, where only 1 example is available for training. It still remains 88.7% in the extreme 36-way-1-shot case. The generalization ability is further validated through three groups of experiment involving unseen shapes, materials and force/speed perturbations. More insights are additionally provided by this work for the interpretation of recognition tasks and improved design of tactile sensors.

Problem

• tactile recognition
• data scarcity
• few-shot learning
• shape and material classification
• meta-learning

Innovation

• meta-learning
• automatic feature optimization
• tactile recognition
• few-shot learning
• prototypical network