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

Abstract

Dexterous manipulation, especially dexterous grasping, is a primitive and crucial ability of robots that allows the implementation of performing human-like behaviors. Deploying the ability on robots enables them to assist and substitute human to accomplish more complex tasks in daily life and industrial production. A comprehensive review of the methods based on point cloud and deep learning for robotics dexterous grasping from three perspectives is given in this paper. As a new category schemes of the mainstream methods, the proposed generation-evaluation framework is the core concept of the classification. The other two classifications based on learning modes and applications are also briefly described afterwards. This review aims to afford a guideline for robotics dexterous grasping researchers and developers.

A Review of Scene Representations for Robot Manipulators

“…In constrast to meshes, point clouds are closer to the native output of commonly used depth cameras, making them more practical for real world construction. Approaches exist for grasp planning directly on point clouds [69,70,71,72], although less numerous than those for meshes. Florence et.…”

Self-Supervised Learning for Joint Pushing and Grasping Policies in Highly Cluttered Environments

“…Autonomous grasping is a challenging problem that has undergone enormous improvement in recent years, especially with Artificial Intelligence (AI) practical approaches. However, robots' dexterity in grasping is one of the most primitive manipulations that allow robots to operate further complex tasks [9]. Classical approaches rely on a modelbased approach, where pre-knowledge of the object model is used to estimate force closures and grasp orientation.…”

“…Then in a simulation setting, the robot exploits the learned visual features to perform a grasp action. The advantage of such an approach is that it does not require explicit knowledge of the objects compared to the classic approaches, i.e., model-based [9]. State-of-the-art and leading work that uses observed geometry to evaluate antipodal grasp pose [12] 1 https://github.com/Kamalnl92/Self-Supervised-Learning-for-pushingand-grasping [13], has sparked enormous interest in the deep learning approach.…”

Dexterous Manipulation for Multi-Fingered Robotic Hands With Reinforcement Learning: A Review

“…Recently, the power of artificial intelligence has attracted the attention of many researchers. Deep learning has even reached a level that exceeds that of humans in certain fields, such as computer vision, so the robot can extract generalized features autonomously (LeCun et al, 2015 ; Duan et al, 2021 ; Wei et al, 2021 , 2022 ; Li et al, 2022 ). Deep learning is better at classification and prediction problems and so on.…”