Motor Control and Robot Learning

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

Deadline for manuscript submissions: closed (10 December 2021) | Viewed by 2433

Special Issue Editors


E-Mail Website
Guest Editor
Humanoid and Cognitive Robotics Lab, Department for Automatics, biocybernetics and robotics, Jožef Stefan Institute, Jamova cesta 39, 1000 Ljubljana, Slovenia
Interests: robot imitation learning; learning by demonstration; manipulation learning; robot compliance; adaptation of robot motion; human–robot cooperation; humanoid robotics; applicative industrial robotics

E-Mail Website
Guest Editor
Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Università della Svizzera Italiana (USI) IDSIA-SUPSI, Manno, Switzerland
Interests: industrial robots; collaborative robots; control theory; wearable robotics; interaction control; human-robot collaboration; AI; ML
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

It is our pleasure to announce the opening of a new Special Issue of Applied Science.

The main topic of the special issue is the advancement of robot learning and motor control algorithms and their application.

Tasks that seem natural to humans are often tricky for robots or artificial agents, furthermore, often they are difficult to implement – to program. Hard-to-engineer robot tasks are being tackled by learning algorithms not only in academic and research environments – robot learning has progressed into all aspects of robot applications and use, be it in industry, rehabilitation, assistive robotics, or in entertainment applications. Robot learning has made giant strides towards making robots capable of performing complex tasks and acting independently in unstructured environments. From learning by demonstration, reinforcement learning, policy search, evolutionary algorithms and the recent success of deep reinforcement learning algorithms, the field is continually pushing the boundaries. That robots are breaking out of factories has become yesterday’s news. Thus, the progress of robot learning has drastically changed the landscape of the applicability of robots. Going hand-in-hand with machine learning and exploiting deep learning techniques, have made robot learning one of the best prospects for technology with the potential to radically change our future. But to change the future, the foundations need to be firm.

This Special Issue is set to present the newest findings, approaches and results in the field of robot learning and motor control, providing an overview of the possibilities of today and the prospect for the future.

Dr. Andrej Gams
Dr. Loris Roveda
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

  • Robot learning
  • Motor control
  • Deep neural networks
  • Robot skill learning
  • Perception–action coupling
  • Motion adaptation

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 1326 KiB  
Article
Generalization-Based Acquisition of Training Data for Motor Primitive Learning by Neural Networks
by Zvezdan Lončarević, Rok Pahič, Aleš Ude and Andrej Gams
Appl. Sci. 2021, 11(3), 1013; https://0-doi-org.brum.beds.ac.uk/10.3390/app11031013 - 23 Jan 2021
Cited by 9 | Viewed by 1846
Abstract
Autonomous robot learning in unstructured environments often faces the problem that the dimensionality of the search space is too large for practical applications. Dimensionality reduction techniques have been developed to address this problem and describe motor skills in low-dimensional latent spaces. Most of [...] Read more.
Autonomous robot learning in unstructured environments often faces the problem that the dimensionality of the search space is too large for practical applications. Dimensionality reduction techniques have been developed to address this problem and describe motor skills in low-dimensional latent spaces. Most of these techniques require the availability of a sufficiently large database of example task executions to compute the latent space. However, the generation of many example task executions on a real robot is tedious, and prone to errors and equipment failures. The main result of this paper is a new approach for efficient database gathering by performing a small number of task executions with a real robot and applying statistical generalization, e.g., Gaussian process regression, to generate more data. We have shown in our experiments that the data generated this way can be used for dimensionality reduction with autoencoder neural networks. The resulting latent spaces can be exploited to implement robot learning more efficiently. The proposed approach has been evaluated on the problem of robotic throwing at a target. Simulation and real-world results with a humanoid robot TALOS are provided. They confirm the effectiveness of generalization-based database acquisition and the efficiency of learning in a low-dimensional latent space. Full article
(This article belongs to the Special Issue Motor Control and Robot Learning)
Show Figures

Figure 1

Back to TopTop