Deep Learning based end-to-end Grasping Pipeline on a lowcost 5-DOF Robotic arm

The problem of robotic grasping is still an unsolved problem with many approaches trying to generalize grasp predictions for unseen and dynamic environments. In this paper, we propose a complete end-to-end pipeline for the task of Deep Learning based robotic grasping on a lowcost 5-DOF arm. We explore Transfer learning approach and then train our grasping model from end-to-end. In the transfer learning approach we tried 2 base models, VGG-16 and ResNet-50. Our grasping model when ResNet-50 is used as base architecture provided better results with a testing accuracy of 83.3% while VGG-16 provided an accuracy of 78.2%. In order to test our model on a real robotic arm, we built a 5-DOF arm and added a custom parallel plate gripper. Complete ROS and Moveit support is added to our developed robotic arm. The processed RG-D image from the KinectV2 camera is given as an input to the model which predicts the 5-D grasp configuration. Required electronic system design and its PCB is built which controls the robotic arm. The predicted 5-D grasp configuration is then transformed to the object pose w.r.t the base link frame of the robot. Lastly, a ROS node is written that automates the task of picking objects lying in different positions & orientations and sends the joint angle values over pyserial communication to the microcontroller’s PCB.