About this Research Topic
Robot grasping is one of the key research areas in robotics. In order to have robots that provide valuable assistance to humans in everyday tasks, they need to be able to physically interact with the environment. However, there are various challenges that needs to be addressed such as scene perception, motion planning, control and safety. The key element of an autonomous grasping solution is the ability to perceive the environment reliably such that the autonomous agent can plan its next actions and ensure that the environment is safe for manipulation.
Various approaches have been proposed for solving the perception problem using cameras, depth sensors, hybrid sensing or various other sensors. Methods such as sensor fusion and human-robot interaction are employed to improve the scene perception. Moreover, recent advancements in machine learning techniques allowed researchers to develop more sophisticated solutions.
The goal of this Research Topic is to promote state of the art research in perception for robot grasping. Perception for grasping is an open-ended problem and there are various challenges that need to be addressed such as scene clutter, dynamic scenes, object detection and scene prediction.
Relevant topics include (but are not limited to):
• 2D/3D object recognition/detection techniques for grasping
• Optimal grasp pose estimation from sensory data
• Scene segmentation for grasping
• Shape completion
• Multi-modal scene understanding
• Pose estimation of objects in 6D
Dr. Hakan Karaoguz is a Senior Data Scientist for Cybercom Group. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
Keywords: Grasping, Sensor Fusion, Perception, Robotics, 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.