Research Topic

Environment Modeling with Computer Vision and AI for Mobile Robotics

About this Research Topic

To fully automate the movement of a mobile robot in an unknown environment either indoors or outdoors, it is essential to build a sufficiently useful model of that environment, so that the robot can move and act efficiently. Computer vision sensors play an important role in this problem, either as the only source of information or in combination with other kinds of sensors, such as laser rangefinders. However, it is necessary to extract relevant information from the scene so that the robot can cope with known and perhaps unexpected situations such as changes in lighting conditions, changes between seasons, presence of other mobile components, structural changes in the environment, etc. The level of complexity imposed by real tasks calls for the robust combination of Computer Vision and AI methods. This Research Topic aims to bring together researchers looking into how these two strands are combined to deliver both the fundamentals and the applications of environmental modeling for mobile robotics.


The development of processing systems has extended the use of Artificial Intelligence (AI) techniques and, among them, Deep Learning (DL) methods in mobile robotics. The use of such techniques in environment modeling using computer vision can be categorized in three main fields. First, AI techniques can be used to create descriptors of the images or to fuse them with other kind of sensory data, extracting relevant information, detecting attention areas in the images, and accounting for the changes that may occur during real operation. Second, they can be used to arrange or classify the information in the map and to include either global or local semantic labels. Finally, once the model is built, AI techniques can be used to solve the localization problem, comparing the current sensory information with the data stored in the map (place recognition). As a result of this comparison, unforeseen elements could be detected and recognized, and also structural changes may be identified and included in the model.


The aim of the current Research Topic is to publish recent developments or applications in the field of environmental modeling, using computer vision and artificial intelligence techniques. The collection is also open to state-of-the-art reviews on these fields.


This Research Topic will cover the specific themes:

• Image processing using AI techniques

• Creating a long-term map of the environment

• Incremental methods to model the environment

• Localization and/or place recognition

• Detection of structural changes and adaption of the model accordingly

• Loop closure detection and/or correction of the model

• Simultaneous Localization and Mapping (SLAM)

• Detection and/or recognition of local elements in the scenes.

• Estimating the trajectory of dynamic components from the scenes

• Multi-sensory information fusion using AI

• Visual odometry and/or movement estimation using AI

• Semantic labelling

• Path planning and control of mobile robots with AI techniques

• Navigation of mobile robots using AI techniques



Keywords: Mobile Robotics, Mapping, Localization, Artificial Intelligence, Machine Learning


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

To fully automate the movement of a mobile robot in an unknown environment either indoors or outdoors, it is essential to build a sufficiently useful model of that environment, so that the robot can move and act efficiently. Computer vision sensors play an important role in this problem, either as the only source of information or in combination with other kinds of sensors, such as laser rangefinders. However, it is necessary to extract relevant information from the scene so that the robot can cope with known and perhaps unexpected situations such as changes in lighting conditions, changes between seasons, presence of other mobile components, structural changes in the environment, etc. The level of complexity imposed by real tasks calls for the robust combination of Computer Vision and AI methods. This Research Topic aims to bring together researchers looking into how these two strands are combined to deliver both the fundamentals and the applications of environmental modeling for mobile robotics.


The development of processing systems has extended the use of Artificial Intelligence (AI) techniques and, among them, Deep Learning (DL) methods in mobile robotics. The use of such techniques in environment modeling using computer vision can be categorized in three main fields. First, AI techniques can be used to create descriptors of the images or to fuse them with other kind of sensory data, extracting relevant information, detecting attention areas in the images, and accounting for the changes that may occur during real operation. Second, they can be used to arrange or classify the information in the map and to include either global or local semantic labels. Finally, once the model is built, AI techniques can be used to solve the localization problem, comparing the current sensory information with the data stored in the map (place recognition). As a result of this comparison, unforeseen elements could be detected and recognized, and also structural changes may be identified and included in the model.


The aim of the current Research Topic is to publish recent developments or applications in the field of environmental modeling, using computer vision and artificial intelligence techniques. The collection is also open to state-of-the-art reviews on these fields.


This Research Topic will cover the specific themes:

• Image processing using AI techniques

• Creating a long-term map of the environment

• Incremental methods to model the environment

• Localization and/or place recognition

• Detection of structural changes and adaption of the model accordingly

• Loop closure detection and/or correction of the model

• Simultaneous Localization and Mapping (SLAM)

• Detection and/or recognition of local elements in the scenes.

• Estimating the trajectory of dynamic components from the scenes

• Multi-sensory information fusion using AI

• Visual odometry and/or movement estimation using AI

• Semantic labelling

• Path planning and control of mobile robots with AI techniques

• Navigation of mobile robots using AI techniques



Keywords: Mobile Robotics, Mapping, Localization, Artificial Intelligence, Machine Learning


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Topic Editors

Loading..

Submission Deadlines

27 July 2021 Abstract
25 January 2022 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..

Topic Editors

Loading..

Submission Deadlines

27 July 2021 Abstract
25 January 2022 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..
Loading..

total views article views article downloads topic views

}
 
Top countries
Top referring sites
Loading..