Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

Journal Browser

Human–Artificial Intelligence (AI) Interaction: Latest Advances and Prospects

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 20 March 2025 | Viewed by 14175

Share This Special Issue

Special Issue Editors

Dr. António Correia

E-Mail Website
Guest Editor

Faculty of Information Technology, University of Jyväskylä, FI-40014 Jyväskylä, Finland
Interests: artificial intelligence; complex systems; computer supported cooperative work; human-AI interaction; hybrid intelligent systems; scientometrics; social computing; science and technology studies
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Daniel Schneider

E-Mail Website
Guest Editor

Postgraduate Program in Informatics (PPGI), Federal University of Rio de Janeiro, Rio de Janeiro 21941-916, Brazil
Interests: computer supported cooperative work; crowdsourcing; digital nomadism; human-computer interaction; social computing; social media
Special Issues, Collections and Topics in MDPI journals

Dr. Benjamim Fonseca

E-Mail Website
Guest Editor

INESC TEC, University of Trás-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal
Interests: collaborative learning; computational thinking; computer supported cooperative work; human-computer interaction; optimization; reinforcement learning
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Tommi Kärkkäinen

E-Mail Website
Guest Editor

Faculty of Information Technology, University of Jyväskylä, FI-40014 Jyväskylä, Finland
Interests: artificial intelligence; data mining; deep learning; educational technology; learning analytics; machine learning; neural networks
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Human-Artificial Intelligence (AI) interaction is on the brink of revolutionizing the world in the coming decades, transforming everything from business operations to household applications. AI empowers systems with the ability to learn, adapt, and make decisions, bringing significant benefits to fields such as medicine, architecture, education, agriculture, and forensics. This transformative technology has redefined the way we interact with the world around us, ushering in a new era of human-AI partnerships where humans use AI-infused systems both implicitly and explicitly to augment their experiences and achieve greater outcomes based on their generative capacity and contextualized meanings in practical uses.

This special issue aims to present the latest advances and perspectives in the area of human-AI interaction. Articles accepted for publication must address topics related to the design, development and evaluation of human-AI interactive systems. We invite both researchers and practitioners to contribute their high-quality original research, reviews, insights, and perspectives on these topics to this special issue.

Topics of interest include but are not limited to:

AI models: AI models used for human-AI interaction, such as conversational agents, recommendation systems, and assisted learning systems.
User interfaces: user interfaces for human-AI interaction systems, such as natural interfaces, graphical interfaces, and virtual reality-based interfaces.
Evaluation of human-AI interactive systems: fieldwork studies (e.g., ethnographically-informed approaches to AI system design) and methods for evaluating human-AI interactive systems such as usability assessment scales, accessibility compliance instruments, and impact assessment methodologies.
Challenges and opportunities of human-AI interaction in real-world settings: potential obstacles and possibilities to implementing human-AI systems in specific application domains, such as collaborative clinical work, digital well-being, misinformation, creativity work, and entertainment.

Dr. António Correia
Dr. Daniel Schneider
Prof.Dr. Benjamim Fonseca
Prof.Dr. Tommi Kärkkäinen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

artificial intelligence
foundation models
human-AI interaction
human-centered generative AI
hybrid intelligent systems
large language models
machine learning
mixed-initiative systems
user experience

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (6 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

16 pages, 1760 KiB

Open AccessArticle

Robot Control Platform for Multimodal Interactions with Humans Based on ChatGPT

by Jingtao Qu, Mateusz Jarosz and Bartlomiej Sniezynski

Appl. Sci. 2024, 14(17), 8011; https://doi.org/10.3390/app14178011 - 7 Sep 2024

Viewed by 2047

Abstract

This paper presents the architecture of a multimodal human–robot interaction control platform that leverages the advanced language capabilities of ChatGPT to facilitate more natural and engaging conversations between humans and robots. Implemented on the Pepper humanoid robot, the platform aims to enhance communication by providing a richer and more intuitive interface. The motivation behind this study is to enhance robot performance in human interaction through cutting-edge natural language processing technology, thereby improving public attitudes toward robots, fostering the development and application of robotic technology, and reducing the negative attitudes often associated with human–robot interactions. To validate the system, we conducted experiments measuring negative attitude robot scale and their robot anxiety scale scores before and after interacting with the robot. Statistical analysis of the data revealed a significant improvement in the participants’ attitudes and a notable reduction in anxiety following the interaction, indicating that the system holds promise for fostering more positive human–robot relationships. Full article

(This article belongs to the Special Issue Human–Artificial Intelligence (AI) Interaction: Latest Advances and Prospects)

► Show Figures

Figure 1

Figure 1
Robot Control Platform for Multimodal Interactions with Humans based on ChatGPT. Full article ">Figure 2
Sequence of interactions in the proposed architecture, highlighting envisioned actions. Full article ">Figure 3
Application working on Pepper robot, user view of the robot during conversation. Full article ">Figure 4
Interaction flow used in experiments. Full article ">Figure 5
Results before and after experiment with NARS survey. Full article ">Figure 6
Results before and after experiment with NARS survey, grouped into three factors: S1—negative attitude towards interaction with robots, S2—negative attitude towards social influence of robots, and S3—negative attitude toward emotions in interaction with robots. Full article ">Figure 7
Results before and after experiment with RAS survey. Full article ">Figure 8
Results before and after experiment with RAS survey, grouped into three factors: S1—anxiety towards communication capability of robots, S2—anxiety towards behavioral characteristics of robots, S3—anxiety towards discourse with robots. Full article ">

27 pages, 6903 KiB

Open AccessArticle

A Real-Time Detection of Pilot Workload Using Low-Interference Devices

by Yihan Liu, Yijing Gao, Lishengsa Yue, Hua Zhang, Jiahang Sun and Xuerui Wu

Appl. Sci. 2024, 14(15), 6521; https://doi.org/10.3390/app14156521 - 26 Jul 2024

Cited by 2 | Viewed by 1526

Abstract

Excessive pilot workload is one of the significant causes of flight accidents. The detection of flight workload can help optimize aircraft crew operation procedures, improve cockpit human–machine interface (HMIs) design, and ultimately reduce the risk of flight accidents. However, traditional detection methods often employ invasive or patch-based devices that can interfere with the pilot’s control. In addition, they generally lack real-time capabilities, while the workload of pilots actually varies continuously. Moreover, most models do not take individual physiological differences into account, leading to the poor performance of new pilots. To address these issues, this study developed a real-time pilot workload detection model based on low-interference devices, including telemetry eye trackers and a pressure-sensing seat cushion. Specifically, the Adaptive KNN-Ensemble Pilot Workload Detection (AKE-PWD) model is proposed, combining KNN in the outer layer for identifying the physiological feature cluster with the ensemble classifier corresponding to this cluster in the inner layer. The ensemble model employs random forest, gradient boosting trees, and FCN–Transformer as base learners. It utilizes soft voting for predictions, integrating the strengths of various networks and effectively extracting the sequential features from complex data. Results show that the model achieves a detection accuracy of 82.6% on the cross-pilot testing set, with a runtime of 0.1 s, surpassing most studies that use invasive or patch-based detection devices. Additionally, the model demonstrates high accuracy across different individuals, indicating good generalization. The results are expected to improve flight safety. Full article

(This article belongs to the Special Issue Human–Artificial Intelligence (AI) Interaction: Latest Advances and Prospects)

► Show Figures

Figure 1

21 pages, 5048 KiB

Open AccessArticle

Open-Source Robotic Study Companion with Multimodal Human–Robot Interaction to Improve the Learning Experience of University Students

by Farnaz Baksh, Matevž Borjan Zorec and Karl Kruusamäe

Appl. Sci. 2024, 14(13), 5644; https://doi.org/10.3390/app14135644 - 28 Jun 2024

Cited by 3 | Viewed by 3233

Abstract

Remote, online learning provides opportunities for flexible, accessible, and personalised education, regardless of geographical boundaries. This study mode also promises to democratise education, making it more adaptable to individual learning styles. However, transitioning to this digital paradigm also brings challenges, including issues related to students’ mental health and motivation and communication barriers. Integrating social robots into this evolving educational landscape presents an effective approach to enhancing student support and engagement. In this article, we focus on the potential of social robots in higher education, identifying a significant gap in the educational technology landscape that could be filled by open-source learning robots tailored to university students’ needs. To bridge this gap, we introduce the Robotic Study Companion (RSC), a customisable, open-source social robot developed with cost-effective off-the-shelf parts. Designed to provide an interactive and multimodal learning experience, the RSC aims to enhance student engagement and success in their studies. This paper documents the development of the RSC, from establishing literature-based requirements to detailing the design process and build instructions. As an open development platform, the RSC offers a solution to current educational challenges and lays the groundwork for personalised, interactive, and affordable AI-enabled robotic companions. Full article

(This article belongs to the Special Issue Human–Artificial Intelligence (AI) Interaction: Latest Advances and Prospects)

► Show Figures

Figure 1

21 pages, 2022 KiB

Open AccessArticle

An Intelligent Human–Machine Interface Architecture for Long-Term Remote Robot Handling in Fusion Reactor Environments

by Tamara Benito and Antonio Barrientos

Appl. Sci. 2024, 14(11), 4814; https://doi.org/10.3390/app14114814 - 2 Jun 2024

Cited by 1 | Viewed by 1591

Abstract

This paper addresses the intricate challenge posed by remote handling (RH) operations in facilities with operational lifespans surpassing 30 years. The extended RH task horizon necessitates a forward-looking strategy to accommodate the continuous evolution of RH equipment. Confronted with diverse and evolving hardware interfaces, a critical requirement emerges for a flexible and adaptive software architecture based on changing situations and past experiences. The paper explores the inherent challenges associated with sustaining and upgrading RH equipment within an extended operational context. In response to this challenge, a groundbreaking, flexible, and maintainable human–machine interface (HMI) architecture named MAMIC is designed, guaranteeing seamless integration with a diverse range of RH equipment developed over the years. Embracing a modular and extensible design, the MAMIC architecture facilitates the effortless incorporation of new equipment without compromising system integrity. Moreover, by adopting this approach, nuclear facilities can proactively steer the evolution of RH equipment, guaranteeing sustained performance and compliance throughout the extended operational lifecycle. The proposed adaptive architecture provides a scalable and future-proof solution, addressing the dynamic landscape of remote handling technology for decades. Full article

(This article belongs to the Special Issue Human–Artificial Intelligence (AI) Interaction: Latest Advances and Prospects)

► Show Figures

Figure 1

Figure 1
MAMIC model generation and integration. Full article ">Figure 2
The four-person work cell tasks. (a) The responsible officer oversees operations. (b) The deputy manages cameras and support tools. (c) The “mover“ operates casks, transporters, and cranes. (d) The “manipulator” controls the master arm and other manipulative devices. Reprinted with permission from Ref. [<a href="#B30-applsci-14-04814" class="html-bibr">30</a>]. 2024, D. Hamilton. Full article ">Figure 3
The ITER Maintenance System serves various areas within the ITER facility. (a) Full capability for its manual maintenance within the hot cell, NB cell, and test stand. (b) Full remote handling capability, including rescue operations, within the in-vessel, hot cell, and NB cell. (c) Complete remote handling capabilities for the recovery of casks within the lift, gallery, and hot cell. (d) Remote handling capabilities that can be seamlessly combined with local manual support within the NB cell, hot cell (part), port cell, and test stand area. Full article ">Figure 4
Software development, verification, and validation lifecycle. Full article ">Figure 5
ITER MAMIC architecture generation integrating (a) driving actors, such as external input devices, third-party frameworks, OMS, and CODAC workstations, (b) driven actors, such as VR, AR, RHDB, and RH robots, and (c) an easy automatic integration testing framework into the different bounded context using the port–adapter pair. Full article ">

19 pages, 11964 KiB

Open AccessArticle

Translating Words to Worlds: Zero-Shot Synthesis of 3D Terrain from Textual Descriptions Using Large Language Models

by Guangzi Zhang, Lizhe Chen, Yu Zhang, Yan Liu, Yuyao Ge and Xingquan Cai

Appl. Sci. 2024, 14(8), 3257; https://doi.org/10.3390/app14083257 - 12 Apr 2024

Viewed by 1394

Abstract

The current research on text-guided 3D synthesis predominantly utilizes complex diffusion models, posing significant challenges in tasks like terrain generation. This study ventures into the direct synthesis of text-to-3D terrain in a zero-shot fashion, circumventing the need for diffusion models. By exploiting the large language model’s inherent spatial awareness, we innovatively formulate a method to update existing 3D models through text, thereby enhancing their accuracy. Specifically, we introduce a Gaussian–Voronoi map data structure that converts simplistic map summaries into detailed terrain heightmaps. Employing a chain-of-thought behavior tree approach, which combines action chains and thought trees, the model is guided to analyze a variety of textual inputs and extract relevant terrain data, effectively bridging the gap between textual descriptions and 3D models. Furthermore, we develop a text–terrain re-editing technique utilizing multiagent reasoning, allowing for the dynamic update of the terrain’s representational structure. Our experimental results indicate that this method proficiently interprets the spatial information embedded in the text and generates controllable 3D terrains with superior visual quality. Full article

(This article belongs to the Special Issue Human–Artificial Intelligence (AI) Interaction: Latest Advances and Prospects)

► Show Figures

Figure 1

Review

Jump to: Research

31 pages, 2972 KiB

Open AccessReview

A Review of Brain–Computer Interface-Based Language Decoding: From Signal Interpretation to Intelligent Communication

by Yingyi Qiu, Han Liu and Mengyuan Zhao

Appl. Sci. 2025, 15(1), 392; https://doi.org/10.3390/app15010392 - 3 Jan 2025

Viewed by 1930

Abstract

Brain–computer interface (BCI) technologies for language decoding have emerged as a transformative bridge between neuroscience and artificial intelligence (AI), enabling direct neural–computational communication. The current literature provides detailed insights into individual components of BCI systems, from neural encoding mechanisms to language decoding paradigms and clinical applications. However, a comprehensive perspective that captures the parallel evolution of cognitive understanding and technological advancement in BCI-based language decoding remains notably absent. Here, we propose the Interpretation–Communication–Interaction (ICI) architecture, a novel three-stage perspective that provides an analytical lens for examining BCI-based language decoding development. Our analysis reveals the field’s evolution from basic signal interpretation through dynamic communication to intelligent interaction, marked by three key transitions: from single-channel to multimodal processing, from traditional pattern recognition to deep learning architectures, and from generic systems to personalized platforms. This review establishes that BCI-based language decoding has achieved substantial improvements in regard to system accuracy, latency reduction, stability, and user adaptability. The proposed ICI architecture bridges the gap between cognitive neuroscience and computational methodologies, providing a unified perspective for understanding BCI evolution. These insights offer valuable guidance for future innovations in regard to neural language decoding technologies and their practical application in clinical and assistive contexts. Full article

(This article belongs to the Special Issue Human–Artificial Intelligence (AI) Interaction: Latest Advances and Prospects)

► Show Figures

Figure 1

Figure 1
The Interpretation–Communication–Interaction (ICI) architecture, showing the three-stage evolution of BCI-based language decoding, from basic signal interpretation through advanced dynamic communication to innovative intelligent interaction, with corresponding architectures, features, and applications at each stage. Full article ">Figure 2
(a) The DRC model of reading processing (adapted from [<a href="#B28-applsci-15-00392" class="html-bibr">28</a>]), showing lexical (vocabulary-based) and non-lexical (letter-to-sound conversion) pathways from print to speech output. (b) The multicomponent Working Memory Model (adapted from [<a href="#B35-applsci-15-00392" class="html-bibr">35</a>]), illustrating interactions between the central executive system and its specialized subsystems (visuo-spatial, episodic, and phonological components), with long-term memory processes. Full article ">Figure 3
(a) The classical Wernicke–Lichtheim–Geschwind language network model (adapted from [<a href="#B52-applsci-15-00392" class="html-bibr">52</a>]), showing the core components of language processing including Broca’s area (orange), Wernicke’s area (red), and their connection via the arcuate fasciculus; (b) distributed connectivity pattern in the Perisylvian language network (adapted from [<a href="#B52-applsci-15-00392" class="html-bibr">52</a>]), illustrating information-specific pathways (green: syntactic, blue: semantic, red: phonological) between Broca’s subregions and posterior language areas. SPL/IPL: superior/inferior parietal lobule; AG: angular gyrus; pSTG: posterior superior temporal gyrus; pMTG: posterior middle temporal gyrus; pITG: posterior inferior temporal gyrus. Full article ">Figure 4
(a) Sequential processing stages of EEGNet (adapted from [<a href="#B63-applsci-15-00392" class="html-bibr">63</a>]), showing temporal filtering (Conv2D), frequency-specific spatial filtering (DepthwiseConv2D), and feature map integration (SeparableConv2D), followed by classification. (b) An integrated deep learning pipeline for neural signal classification (adapted from [<a href="#B67-applsci-15-00392" class="html-bibr">67</a>]), demonstrating the sequential stages of data augmentation, feature selection, feature extraction, and classification. Full article ">Figure 5
End-to-end architecture for decoding speech from brain signals using wav2vec 2.0 and contrastive learning (adapted from [<a href="#B14-applsci-15-00392" class="html-bibr">14</a>]); wav2vec: wave-to-vector; CLIP: contrastive language–image pre-training; Conv: convolution. Full article ">

Show export options Show export options

Select all

Export citation of selected articles as:

Displaying articles 1-6

Journal Menu

Journal Browser

Human–Artificial Intelligence (AI) Interaction: Latest Advances and Prospects

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (6 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI