YOLOv3 Case Study: Deep Learning Approach For Detection and Performance of Action Using Soft Hand

Authors

  • Prof. Dr.Kamal Alaskar, Mr. Abdulrashid Kamal Alaskar

Abstract

There are lots of ways used to pick or grasp object through robotic hand but there are some hardly worked done with help the of Deep Learning approaches. To solve this issue, a solution is proposed which involves human strategies of picking up an object using Neural Network classifier. Classifier uses help of object detection model to detect object in environment and classifier classifies into picking strategy as per objects shape and orientation. Strategy detected by classifier can be used by soft hand as anticipatory action and reactive grasp. To increase accuracy number of primitive measures taken into consideration, our bounded and some of limitation are taken into mind while proposing architecture.

 Keywords- Deep learning, Grasping Strategies, Neural Network, Soft Hand.

Published

2020-12-31

Issue

Section

Articles