Recent Advances and Applications of Optimal Control and Reinforcement Learning in Guidance and Navigation Systems
A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Mechanical Engineering".
Deadline for manuscript submissions: closed (20 August 2021) | Viewed by 12945
Special Issue Editors
Interests: optimal control and reinforcement learning with applications to aerospace systems
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Optimal control approach has provided fruitful solutions in many engineering problems such as guidance, navigation and control systems for last few decades. It widened understanding of complex control systems and contributed to flourishing of modern control systems. However, it is considered as a theoretical designing method that results in complex actions which heavily relies on well-specified mathematical models.
On the other hand, reinforcement learning makes model-free predictions and produces actions from the data obtained by interacting with complex environments. Recently, the dramatic progress in reinforcement learning has opened tremendous opportunities in various fields of science and engineering. It is also expected to be able to play an important role in more challenging guidance, navigation, and control applications, including autonomous cars, robots and aerial systems that require agile dynamics.
However, considering its potential, current reinforcement learning is only at the starting point, and has many challenges to overcome. Among them, developing efficient ways of using big data and guaranteeing safe and reliable interaction with a complex and uncertain environment are the main issues. Since the efficiency, safety and reliability problems are also the core topics of the optimal control theory, combining the existing optimal control and reinforcement learning theories shows great possibility of compensating the weaknesses of each and wide acceptance for practical applications.
The aim of this Special Issue is to invite papers for recent advances in theory and applications of optimal control and reinforcement learning in guidance, navigation and control systems, as well as to exploit the novel results of the combination of optimal control and reinforcement learning technology for unmanned vehicles, robots, or any dynamics systems. Potential topics of the Special Issue include, but are not limited to, the following:
- emerging technology in optimal control and reinforcement learning
- novel applications of optimal control and reinforcement learning in guidance, navigation and control systems
- combination of optimal control and reinforcement learning technology
- reinforcement learning based path planning and tracking.
- reinforcement learning based modeling and parameter optimization
- supplementing method of reinforcement learning using optimal control theory
- structure and training method of deep reinforcement learning networks
Prof. Sungsu Park
Prof. Keeyoung Choi
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
- optimal control
- reinforcement learning
- guidance, navigation and control
- path planning and tracking
- deep neural network
- autonomous vehicle
