Comprehensive Review on Reaching and Grasping of Objects in Robotics

Abstract

SUMMARY Interaction between a robot and its environment requires perception about the environment, which helps the robot in making a clear decision about the object type and its location. After that, the end effector will be brought to the object’s location for grasping. There are many research studies on the reaching and grasping of objects using different techniques and mechanisms for increasing accuracy and robustness during grasping and reaching tasks. Thus, this paper presents an extensive review of research directions and topics of different approaches such as sensing, learning and gripping, which have been implemented within the current five years.

Interception of an aerial manoeuvring target using monocular vision

“…A good survey about reaching and grasping of objects with a manipulator using visual information is provided in ref. [18].…”

Learning Pick to Place Objects using Self-supervised Learning with Minimal Training Resources

“…Robotics can be used in nearly every circumstance, but particularly in cluttered environments, where the need for enhanced grasping efficiency demands. Object grasping is a typical robotics challenge that has made substantial progress in recent years, which is an essential step in many robotic tasks [4]. Objects removal task has been extensively researched in many studies.…”

“…Recently, a standard Deep-RL has been used in a variety of robotic applications [6], including placement [7], grasping deformable objects [8], and grasping in a cluttered environment [5]. Meanwhile, it has advanced technology by integrating visual and tactile input, particularly in robotic grasping [4]. Additionally, deep-RL has offered great solutions for difficult-to-perform and repeat tasks via the use of end-to-end training.…”

Designing a Low-Cost Mechatronic Device for Semi-Automatic Saffron Harvesting

“…In general, the end-effector is the main interface between the object to be manipulated and the user, as pointed out in several applications for the mechanical harvesting of horticultural products, such as reported for example in [8,9]. The literature reports multiple attempts of robotic hands for grasping objects [10][11][12][13][14], with some specific end-effectors designed for robotic harvesting such as reported in [15,16]. The main limitations of the existing solutions are that they are mostly designed for singleproduct applications [17,18], like tomatoes [19], strawberries [20] or cucumbers [21] while they result in being unsuitable for the mechanical harvesting of saffron, in particular, for the high fragility of saffron flowers where excessive applied forces will be strongly detrimental to the final quality of the spice.…”