Simulation of Robotic Arm Grasping Control Based on Proximal Policy Optimization Algorithm

Abstract

There are many kinds of inverse kinematics solutions for robots. Deep reinforcement learning can make the robot spend a short time to find the optimal inverse kinematics solution. Aiming at the problem of sparse rewards in the process of deep reinforcement learning, this paper proposes an improved PPO algorithm. Firstly, built a simulation environment for the operation of the robotic arm. Secondly, use a convolutional neural network to process the data read by the camera of the robotic arm, obtaining a network about Actor and Critic. Thirdly, based on the principle of inverse kinematics of the robotic arm and the reward mechanism in deep reinforcement learning, design a hierarchical reward function containing motion accuracy to promote the convergence of the PPO algorithm. Finally, compare the improved PPO algorithm with the traditional PPO algorithm. The results show that the improved PPO algorithm has improved both the convergence speed and the operating accuracy.

Detection-driven 3D masking for efficient object grasping

“…Object detection consists of identifying and locating objects in a visual scene. By detecting and recognizing objects in images or videos, the robot can determine the object position, the category of the object well as esti-mating the grasping pose from the detection informa-tion [18,19,20,21]. Examples related to grasping are PoseCNN [8], Faster R-CNN Inception-V2 [22] and partial depth estimation [23] all of which have achieved good results and are widely applied.…”