Feature Sensing and Robotic Grasping of Objects with Uncertain Information: A Review

Abstract

<jats:p>As there come to be more applications of intelligent robots, their task object is becoming more varied. However, it is still a challenge for a robot to handle unfamiliar objects. We review the recent work on the feature sensing and robotic grasping of objects with uncertain information. In particular, we focus on how the robot perceives the features of an object, so as to reduce the uncertainty of objects, and how the robot completes object grasping through the learning-based approach when the traditional approach fails. The uncertain information is classified into geometric information and physical information. Based on the type of uncertain information, the object is further classified into three categories, which are geometric-uncertain objects, physical-uncertain objects, and unknown objects. Furthermore, the approaches to the feature sensing and robotic grasping of these objects are presented based on the varied characteristics of each type of object. Finally, we summarize the reviewed approaches for uncertain objects and provide some interesting issues to be more investigated in the future. It is found that the object’s features, such as material and compactness, are difficult to be sensed, and the object grasping approach based on learning networks plays a more important role when the unknown degree of the task object increases.</jats:p>

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

“…Ruiz-del-Solar et al ( 2018 ) and Du et al ( 2020 ) pay attention to the vision methods for robot manipulations. With the exception of visual perception approaches, Luo et al ( 2017 ) and Wang C. et al ( 2020 ) exhibit there are many other perception methods can help improve robot performance. Caldera et al ( 2018 ), Kroemer et al ( 2019 ), Li and Qiao ( 2019 ), and Kleeberger et al ( 2020 ) focus on the overview of robot manipulation methods based on deep learning.…”

A Multimodal Intention Detection Sensor Suite for Shared Autonomy of Upper-Limb Robotic Prostheses

“…Similarly, a deep learning-based vision system was proposed by Ghazaei et al [28], in which a CNN classifier was utilized to determine the grasp pattern without explicitly identifying the object dimensions. More recently, a technique was developed that combines deep learning and gaze information to classify objects and estimate its pose for grasping [29] and a novel method was proposed to categorize unfamiliar objects based on uncertain information derived from the features of the object [30].…”

Sensitivities of Rheological Properties of Magnetoactive Foam for Soft Sensor Technology

“…A soft sensor is an advanced technology that is capable of handling small-scale tasks with high accuracy. The technology requires highly compliant, soft, flexible and squishy materials to produce touch devices with high flexibility and sensitivity such as soft grippers, prosthetic hands, human motor systems, biomedical robots, and field robots for data collection [ 1 , 2 , 3 ]. One of the main components in a soft sensor is a smart material that is capable of measuring physical quantities such as force, displacement, heat, etc., before converting them into an electrical signal, which can then be used in an electrical circuit or microprocessor to generate a readable response for an actuator.…”