Abstract
Advancements in robotics and AI have increased the demand for interactive robots in healthcare and assistive applications. However, ensuring safe and effective physical human-robot interactions (pHRIs) remains challenging due to the sophistication of human motor communication and intent recognition. Traditional physics-based models struggle to capture the dynamic nature of human force interactions, limiting robot adaptability. To address these limitations, neural networks (NNs) have been explored for force-movement intention prediction. While multi-layer perceptron (MLP) networks show potential, they struggle with temporal dependencies and generalization. Long Short-Term Memory (LSTM) networks effectively model sequential dependencies, while Convolutional Neural Networks (CNNs) enhance spatial feature extraction from human force data. Building on these strengths, this study introduces a hybrid LSTM-CNN framework to improve force-movement intention prediction, increasing accuracy from 69% to 86% through effective denoising and advanced architectures. The combined CNN-LSTM network proved particularly effective in handling individualized force-velocity relationships and presents a generalizable model paving the way for more adaptive strategies in robot guidance. These findings highlight the importance of integrating spatial and temporal modeling to enhance robot precision, responsiveness, and human-robot collaboration.
Recommended Citation
Zadeh, K. G., Zendehdel, N., Holmes, G. L., Bonnett, K. M., Costa, A., Burns, D. M., Leu, M., & Song, Y. S. (2025). Comparison of CNN and LSTM Networks on Human Intention Prediction in Physical Human-Robot Interactions. IEEE International Conference on Automation Science and Engineering, pp. 2408-2413. Institute of Electrical and Electronics Engineers.
The definitive version is available at https://doi.org/10.1109/CASE58245.2025.11163783
Department(s)
Psychological Science
Second Department
Mechanical and Aerospace Engineering
Keywords and Phrases
Intention Detection; Long-Short Term Memory (LSTM); Machine Learning; Physical Human-Robot Interaction
International Standard Serial Number (ISSN)
2161-8089; 2161-8070
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Jan 2025
Comments
Missouri University of Science and Technology, Grant 1843892