Recent Advances in Intelligent Control Methods for Soft Robotics

Dear Colleagues,

In the last two decades, soft robots have been at the forefront of robotics research because of several advantages offered by their compliant structure (e.g., due to the adaptability in unstructured environments) in contrast to rigid robots typically applied in industry. However, the price paid for this softness takes the form of more challenging modeling and control, where several important aspects, such as infinite-degrees-of-freedom continuum structures as well as the presence of significant hysteresis/creep effects or other nonlinear and time-varying properties, need to be taken into account. Machine learning techniques can address these issues using either model-free or hybrid approaches.

This Special Issue is dedicated to the latest advances in the field of machine learning with application to soft robotics, either to any soft robot component (e.g., soft actuators or sensors) or to robots as a whole. Especially welcome are deep learning models and methods as well as the use of third-generation neural networks (SNNs). The topics include (but are not limited to):

• Kinematics and dynamics modeling of soft continuum robots using neural networks.
• Deep reinforcement learning of soft robots.
• Visual feedback control of soft robots using ML techniques.
• Hyperparameter and structure-optimized DNNs for soft robot modeling and control.
• Spiking neural networks for control of soft robots.
• Unsupervised ML methods in soft sensors/actuators.
• Practical implementations of real-time control of soft robots using ML models.

Dr. Alexander Hošovský
Guest Editor

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. Actuators is an international peer-reviewed open access monthly 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.

• convolutional neural networks
• (deep) recurrent neural networks
• (deep) reinforcement learning
• support vector machines
• feedforward neural networks
• autoencoders and generative adversial networks
• spiking neural networks
• bio-inspired optimization methods
• soft sensors and actuators