Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.6
Journals
Electronics
Special Issues
Artificial Intelligence for Robotics
share announcement

Artificial Intelligence for Robotics

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Systems & Control Engineering".

Deadline for manuscript submissions: closed (15 November 2024) | Viewed by 4564

Special Issue Editors

Prof. Dr. Tao Wang

E-Mail Website
Guest Editor
School of Computer Science, Peking University, Beijing 100871, China
Interests: affective computing; intelligent robot system; computer architecture
Dr. Yimin Zhang

E-Mail Website
Guest Editor
Intel Labs China, Beijing 100086, China
Interests: robot continual learning; elderly care robot; AI system combining vision and language technology; computer vision; natural language understanding
Dr. Liang Zhang

E-Mail Website
Guest Editor
Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly, Nanyang Technological University, N4-B3b-6, 50 Nanyang Avenue, Singapore
Interests: scalable virtual environments; artificial intelligence; mobile computing; cyber security
Dr. Junbin Liu

E-Mail Website
Guest Editor
Syrius Research Institute, Syrius Robotics Co., Ltd., Shenzhen, China
Interests: robotics (planning and control, localization, multi-robot systems); multi-agent systems (cooperative behavior, distributed problem solving)

Special Issue Information

Dear Colleagues,

We are pleased to announce a call for contributions to this Special Issue, entitled "Artificial Intelligence for Robotics", in the AI section of Electronics. This Special Issue aims to explore the exciting advancements and latest research at the intersection of artificial intelligence (AI) and robotics. We invite researchers from academia and industry to contribute their original research papers and review articles in this rapidly evolving field.

Scope of the Special Issue:

The integration of AI techniques and algorithms into robotic systems has revolutionized the capabilities of robots, enabling them to perceive, reason, learn, and interact with the world in a more intelligent and autonomous manner. This Special Issue aims to cover a wide range of topics related to AI for robotics, including, but not limited to, the following:

  1. Perception and sensing: AI-driven approaches for visual perception, object recognition, sensor fusion, localization, mapping, and scene understanding in robotic systems.
  2. Robot motion planning and control: highlighting AI-based approaches for robot motion planning, obstacle avoidance, and trajectory optimization in complex environments.
  3. Robotic manipulation and grasping: AI-based approaches for robotic manipulation, including object recognition, grasp planning, dexterous manipulation, and tactile sensing.
  4. AI in robot control systems: discussions on integrating AI techniques, such as machine learning and control theory, into robot control systems for improved performance and adaptability.
  5. Robot learning and adaptation: machine learning techniques for robotics, including deep learning, transfer learning, zero/few shot learning, continual learning, reinforcement learning, imitation learning, and lifelong learning, enabling robots to acquire new skills, adapt to changing environments, and improve performance over time.
  6. Large language models for robotics AI: integrating large language models into existing robotics AI to expand AI’s horizon, and mitigating robustness and hallucination issues.
  7. Affective computing for robots: AI-based algorithms and techniques for enabling robots to perceive, interpret, and respond to human emotions and affective states, fostering more natural and empathetic interactions.
  8. Human–robot interaction: AI-driven techniques for enhancing human–robot interaction, including natural language processing, speech recognition, gesture recognition, affective computing, and social robotics.
  9. Swarm robotics and multi-robot systems: exploration of AI techniques applied to swarm robotics and multi-robot systems, addressing collective decision-making, swarm intelligence, and self-organization.
  10. Robot companion for the elderly: AI techniques and robotic systems designed to provide companionship, assistance, and support to the elderly population, promoting their well-being, safety, and independence.
  11. Autonomous and intelligent robots in real-world environments: development and application of autonomous and intelligent robots that can perceive, reason, and make decisions in real-world environments, including healthcare, manufacturing, logistics, transportation, and service domains.
  12. Ethical and social implications: ethical and social considerations related to AI in robotics, including fairness, transparency, interpretability, safety, privacy, accountability, reliability and the impact of automation on society.

We look forward to receiving your ground-breaking contributions and sharing the latest advancements in AI for robotics with the global research community.

Sincerely,

Prof. Dr. Tao Wang
Dr. Yimin Zhang
Dr. Liang Zhang
Dr. Junbin Liu
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. Electronics 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

  • AI for robotics
  • perception and sensing
  • motion manipulation, planning and control
  • robot learning
  • large language models
  • affective computing
  • human–robot interaction
  • ethical AI

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 polices can be found here.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 4951 KiB  
Article
S2AC: Self-Supervised Attention Correlation Alignment Based on Mahalanobis Distance for Image Recognition
by Zhi-Yong Wang, Dae-Ki Kang and Cui-Ping Zhang
Electronics 2023, 12(21), 4419; https://doi.org/10.3390/electronics12214419 - 26 Oct 2023
Cited by 1 | Viewed by 1094
Abstract
Susceptibility to domain changes for image classification hinders the application and development of deep neural networks. Domain adaptation (DA) makes use of domain-invariant characteristics to improve the performance of a model trained on labeled data from one domain (source domain) on an unlabeled [...] Read more.
Susceptibility to domain changes for image classification hinders the application and development of deep neural networks. Domain adaptation (DA) makes use of domain-invariant characteristics to improve the performance of a model trained on labeled data from one domain (source domain) on an unlabeled domain (target) with a different data distribution. But existing DA methods simply use pretrained models (e.g., AlexNet, ResNet) for feature extraction, which are convolutional models that are trapped in localized features and fail to acquire long-distance dependencies. Furthermore, many approaches depend too much on pseudo-labels, which can impair adaptation efficiency and lead to unstable and inconsistent results. In this research, we present S2AC, a novel approach for unsupervised deep domain adaptation, that makes use of a stacked attention architecture as a feature map extractor. Our method can fuse domain discrepancy with minimizing a linear transformation of the second statistics (covariances) extended by the p-norm, while simultaneously designing pretext tasks on heuristics to improve the generality of the learning representation. In addition, we have developed a new trainable relative position embedding that not only reduces the model parameters but also enhances model accuracy and expedites the training process. To illustrate our method’s efficacy and controllability, we designed extensive experiments based on the Office31, Office_Caltech_10, and OfficeHome datasets. To the best of our knowledge, the proposed method is the first attempt at incorporating attention-based networks and self-supervised learning for image domain adaptation, and has shown promising results. Full article
(This article belongs to the Special Issue Artificial Intelligence for Robotics)
►▼ Show Figures

Figure 1

22 pages, 7689 KiB  
Article
Tikhonov-Tuned Sliding Neural Network Decoupling Control for an Inverted Pendulum
by Yi-Jen Mon
Electronics 2023, 12(21), 4415; https://doi.org/10.3390/electronics12214415 - 26 Oct 2023
Viewed by 1183
Abstract
This paper introduces the concept of intelligent control using Tikhonov regularization for nonlinear coupled systems. This research is driven by the increasing demand for advanced control techniques and aims to explore the impact of Tikhonov regularization on these systems. The primary objective is [...] Read more.
This paper introduces the concept of intelligent control using Tikhonov regularization for nonlinear coupled systems. This research is driven by the increasing demand for advanced control techniques and aims to explore the impact of Tikhonov regularization on these systems. The primary objective is to determine the optimal regularization term and its integration with other control methods to enhance intelligent control for nonlinear coupled systems. Tikhonov regularization is a technique employed to adjust neural network weights and prevent overfitting. Additionally, the incorporation of ReLU activation function in the neural network simplifies thearchitecture, avoiding issues like gradient explosion, and optimizes controller performance. Furthermore, sliding surfaces are designed to improve control system stability and robustness. The proposed Tikhonov-tuned sliding neural network (TSN) controller ensures both stability and superior system performance. The methodology emphasizes the importance of determining optimal neural network weights and regularization terms to prevent overfitting, facilitating accurate predictions in inverted pendulum control system applications. To assess the functionality and stability of TSN, this paper employs simulations and experimental implementations to control both the rotary inverted pendulum and the arm-driven inverted pendulum. The results indicate that the proposed TSN methodologies are effective and feasible. Full article
(This article belongs to the Special Issue Artificial Intelligence for Robotics)
►▼ Show Figures

Figure 1

23 pages, 7523 KiB  
Article
An Effective Obstacle Avoidance and Motion Planning Design for Underwater Telescopic Arm Robots Based on a Tent Chaotic Dung Beetle Algorithm
by Huawei Jin, Haitao Ji and Fangzheng Yan
Electronics 2023, 12(19), 4128; https://doi.org/10.3390/electronics12194128 - 3 Oct 2023
Cited by 8 | Viewed by 1694
Abstract
As the underwater environment is complex, the existence of obstacles will produce a certain collision interference to underwater robot operations, which causes the overall path planning and time costs to increase. In this paper, we propose a Tent chaotic mapping and dung beetle [...] Read more.
As the underwater environment is complex, the existence of obstacles will produce a certain collision interference to underwater robot operations, which causes the overall path planning and time costs to increase. In this paper, we propose a Tent chaotic mapping and dung beetle hybrid algorithm (MDBO) application for trajectory optimal planning and effective obstacle avoidance for an underwater telescopic arm robot. The method invokes the unique obstacle avoidance habit and foraging optimization idea of the dung beetle algorithm. Introducing it into the chaotic Tent mapping idea prevents the dung beetle algorithm (DBO) from falling into local optimality and increases the coverage of a global search. Simulation results show that the MDBO algorithm exhibits strong optimization ability and stability when multiple algorithms are verified using eight test functions. The MATLAB test reflects the performance indexes of the six joints of the underwater telescopic arm, and compared with various algorithms, the MDBO algorithm has an obvious convergence trend and strong global search ability. The algorithm is applied to real underwater experiments to verify that the improved dung beetle algorithm has better obstacle avoidance ability and reduces trajectory planning time by 30%, which helps the underwater robot to complete motion planning. Full article
(This article belongs to the Special Issue Artificial Intelligence for Robotics)
►▼ Show Figures

Graphical abstract

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop