Learning Collision Situation to Convolutional Neural Network Using Collision Grid Map Based on Probability Scheme

• Main Authors: Jun Hyeong Jo, Chang-bae Moon
• Format: Article
• Language: English
• Published: MDPI AG 2020-01-01
• Series: Applied Sciences
• Subjects: 3d point cloud; classification; convolutional neural network
• Online Access: https://www.mdpi.com/2076-3417/10/2/617

In this paper, a Collision Grid Map (CGM) is proposed by using 3d point cloud data to predict the collision between the cattle and the end effector of the manipulator in the barn environment. The Generated Collision Grid Map using x-y plane and depth z data in 3D point cloud data is applied to a Convolutional Neural Network to predict a collision situation. There is an invariant of the permutation problem, which is not efficiently learned in occurring matter of different orders when 3d point cloud data is applied to Convolutional Neural Network. The Collision Grid Map is generated by point cloud data based on the probability method. The Collision Grid Map scheme is composed of a 2-channel. The first channel is constructed by location data in the x-y plane. The second channel is composed of depth data in the z-direction. 3D point cloud is measured in a barn environment and created a Collision Grid Map. Then the generated Collision Grid Map is applied to the Convolutional Neural Network to predict the collision with cattle. The experimental results show that the proposed scheme is reliable and robust in a barn environment.