Progress and Prospects of Evolutionary Robotics

Dear Colleagues,

Traditional ways of designing robots have shown success mainly in controlled and well-understood environments. However, as applications for robots grow, the environments they will operate in become less controllable, and the development of new robot materials (soft robotics, for example) make these traditional design methods less applicable. One area that is becoming more popular for robot design is Evolutionary Robotics. The majority of work in Evolutionary Robotics has either been achieved in simulation or studies using evolution on physical robots using fixed robotic hardware. The evolution of morphologies (and control systems) has been addressed in artificial life in simulated worlds with virtual creatures. Recent work has addressed the evolution of morphologies in novel substrates and soft materials, but in both cases, evolution took place in simulation and only the final morphologies were physically constructed post evolution. In the majority of work in Evolutionary Robotics to date, simulated and real trials are weakly linked and evolution in simulation is the primary process. A major question that still remains is how to evolve complete robots (bodies and brains) in real time and real space in a rich morphological space that enables closed-loop control by incorporating a range of sensors, multiple type of actuator and free-form skeletons. This would move the state of the art by concurrently running virtual and physical evolution integrated with bi-directional migration and cross-fertilisation between virtual and physical individuals.

This Special Issue invites the submission of papers that present new methods, approaches, designs, concepts and software tools for Evolutionary Robotics. Potential topics include, but are not limited to, the following: novel methods for simultaneous evolution of morphology and/or control, novel methods for facilitating learning and/or adaptation during lifetime, robot evolution in hardware and evolution of morphologies using novel materials.

Prof. Dr. Andy Tyrrell
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. Robotics 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 1800 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.

• evolution
• morphology
• control
• learning
• adaptation
• populations
• intelligence
• hardware
• reality gap