About this Research Topic
Robot grasping describes a robots ability to grasp and manipulate objects. Topics involved in robot grasping range from the mechatronic design of grippers to upper-level cognitive planning of actions.
On the one hand, robot grasping is one of the hardest problems in robotics, since it has to deal with complex perception issues, planning and executing difficult and careful interactions, and requires advanced devices and reasoning.
On the other hand, grasping is one of the most desired abilities for a fully functional robot system in many applications. As a consequence, it is a field which has attracted, and still does, a great deal of interest and research over the last decades, which has resulted in many advances and an active area of research and development.
The goal of this Research Topic is to present the readers with a coherent view of relevant problems in the realm of robot grasping and its most recent advances.
In the last few years, research related to robot grasping has focused on two main aspects. The first is the application of deep learning techniques to robot grasping in order to apprehend and overcome most of the difficult cognitive problems. These applications have not only addressed the perception, but also the planning and control aspects of grasping. The second aspect is the design of novel grippers or robot hands applying principles of soft mechanisms, with the purpose of providing more adaptable and versatile devices.
Nevertheless, other more traditional research lines are still present and should not be neglected in a complete view of robot grasping. These include perception, mostly vision but also haptics; planning, which involves grasp synthesis, analysis and metrics; control and specific applications.
A particularly interesting application of robot grasping is related to hand prostheses, which can benefit from many of the techniques developed for artificial robot hands.
The Research Topic aims to address themes including, but not limited to, the following:
● Perception for grasping: visual analysis of scenes, object reconstruction and recognition, tactile exploration; use and integration of various perceptual modalities.
● Cognition for grasping: grasp synthesis and analysis, analytical and data-driven approaches, learning, planning.
● Control and grasp execution: reactive grasping and other control schemes.
● Benchmarking and evaluations: indexes, metrics and benchmark tasks.
● Applications: implementation of grasping systems and their application to real-world problems.
Topic Editor Beatriz Leon is employed by Shadow Robot Company. All other Topic Editors declare no competing interests with regard to the Research Topic subject.
Please note that submitting an abstract is not mandatory, however, we would encourage you to do so.
Keywords: Robot hands, Robot manipulation, Robot perception, Machine learning, Robot control, System integration
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.