Neural-Network-Driven Intention Recognition for Enhanced Human–Robot Interaction: A Virtual-Reality-Driven Approach

Intention recognition in Human–Robot Interaction (HRI) is critical for enabling robots to anticipate and respond to human actions effectively. This study explores the application of deep learning techniques for the classification of human intentions in HRI, utilizing data collected from Virtual Real...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Kamali Mohammadzadeh, Elnaz Alinezhad, Sara Masoud
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Machines
Subjects:
Online Access:https://www.mdpi.com/2075-1702/13/5/414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257266994839552
author Ali Kamali Mohammadzadeh
Elnaz Alinezhad
Sara Masoud
author_facet Ali Kamali Mohammadzadeh
Elnaz Alinezhad
Sara Masoud
author_sort Ali Kamali Mohammadzadeh
collection DOAJ
description Intention recognition in Human–Robot Interaction (HRI) is critical for enabling robots to anticipate and respond to human actions effectively. This study explores the application of deep learning techniques for the classification of human intentions in HRI, utilizing data collected from Virtual Reality (VR) environments. By leveraging VR, a controlled and immersive space is created, where human behaviors can be closely monitored and recorded. Ensemble deep learning models, particularly Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Transformers, are trained on this rich dataset to recognize and predict human intentions with high accuracy. While CNN and CNN-LSTM models yielded high accuracy rates, they encountered difficulties in accurately identifying certain intentions (e.g., standing and walking). In contrast, the CNN-Transformer model outshone its counterparts, achieving near-perfect precision, recall, and F1-scores. The proposed approach demonstrates the potential for enhancing HRI by providing robots with the ability to anticipate and act on human intentions in real time, leading to more intuitive and effective collaboration between humans and robots. Experimental results highlight the effectiveness of VR as a data collection tool and the promise of deep learning in advancing intention recognition in HRI.
format Article
id doaj-art-744104d3f81b41b49ba8a0f0ad09cb1d
institution OA Journals
issn 2075-1702
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Machines
spelling doaj-art-744104d3f81b41b49ba8a0f0ad09cb1d2025-08-20T01:56:28ZengMDPI AGMachines2075-17022025-05-0113541410.3390/machines13050414Neural-Network-Driven Intention Recognition for Enhanced Human–Robot Interaction: A Virtual-Reality-Driven ApproachAli Kamali Mohammadzadeh0Elnaz Alinezhad1Sara Masoud2Department of Industrial and Systems Engineering, Wayne State University, Detroit, MI 48202, USADepartment of Industrial and Systems Engineering, Wayne State University, Detroit, MI 48202, USADepartment of Industrial and Systems Engineering, Wayne State University, Detroit, MI 48202, USAIntention recognition in Human–Robot Interaction (HRI) is critical for enabling robots to anticipate and respond to human actions effectively. This study explores the application of deep learning techniques for the classification of human intentions in HRI, utilizing data collected from Virtual Reality (VR) environments. By leveraging VR, a controlled and immersive space is created, where human behaviors can be closely monitored and recorded. Ensemble deep learning models, particularly Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Transformers, are trained on this rich dataset to recognize and predict human intentions with high accuracy. While CNN and CNN-LSTM models yielded high accuracy rates, they encountered difficulties in accurately identifying certain intentions (e.g., standing and walking). In contrast, the CNN-Transformer model outshone its counterparts, achieving near-perfect precision, recall, and F1-scores. The proposed approach demonstrates the potential for enhancing HRI by providing robots with the ability to anticipate and act on human intentions in real time, leading to more intuitive and effective collaboration between humans and robots. Experimental results highlight the effectiveness of VR as a data collection tool and the promise of deep learning in advancing intention recognition in HRI.https://www.mdpi.com/2075-1702/13/5/414intention recognitionhuman–robot interactionvirtual realityneural networks
spellingShingle Ali Kamali Mohammadzadeh
Elnaz Alinezhad
Sara Masoud
Neural-Network-Driven Intention Recognition for Enhanced Human–Robot Interaction: A Virtual-Reality-Driven Approach
Machines
intention recognition
human–robot interaction
virtual reality
neural networks
title Neural-Network-Driven Intention Recognition for Enhanced Human–Robot Interaction: A Virtual-Reality-Driven Approach
title_full Neural-Network-Driven Intention Recognition for Enhanced Human–Robot Interaction: A Virtual-Reality-Driven Approach
title_fullStr Neural-Network-Driven Intention Recognition for Enhanced Human–Robot Interaction: A Virtual-Reality-Driven Approach
title_full_unstemmed Neural-Network-Driven Intention Recognition for Enhanced Human–Robot Interaction: A Virtual-Reality-Driven Approach
title_short Neural-Network-Driven Intention Recognition for Enhanced Human–Robot Interaction: A Virtual-Reality-Driven Approach
title_sort neural network driven intention recognition for enhanced human robot interaction a virtual reality driven approach
topic intention recognition
human–robot interaction
virtual reality
neural networks
url https://www.mdpi.com/2075-1702/13/5/414
work_keys_str_mv AT alikamalimohammadzadeh neuralnetworkdrivenintentionrecognitionforenhancedhumanrobotinteractionavirtualrealitydrivenapproach
AT elnazalinezhad neuralnetworkdrivenintentionrecognitionforenhancedhumanrobotinteractionavirtualrealitydrivenapproach
AT saramasoud neuralnetworkdrivenintentionrecognitionforenhancedhumanrobotinteractionavirtualrealitydrivenapproach