Robot global path planning method based on deeply enhanced learning

Abstract

The invention proposes a robot global path planning method based on deeply enhanced learning, which belongs to the robot learning and global path planning technology fields. The method comprises: in the training session: firstly, installing a top-view camera in a scenario; constructing a deep neural network; after a training path is created, outputting the executing actions by the deep neural network according to the images photographed by the camera; and according to the execution effect of the actions, optimizing the parameters of the deep neural network; then, updating the position of a target; performing different path planning trainings to obtain a final deep neural network; and in the execution session: outputting the executing actions for the robot by the final deep neural network according to the images photographed by the camera so that the robot executes the actions; and if the robot reaches the position of the target after its execution of the actions, then, completing the global path planning by the robot. The method of the invention is very practical in use, does not require manual participation, or the entrance of a scenario for constructing an environment map in advance. The method can be applied to multiple scenarios at a low cost.

Description

technical field [0001] The invention relates to a robot global path planning method based on deep reinforcement learning, which belongs to the field of machine learning and the technical field of global path planning. Background technique [0002] In recent years, robotics has become one of the rapidly developing important industries in the high-tech field, and global path planning technology is an important field of robotics research. A good robot global path planning technology can reduce the robot's working time, reduce energy consumption, improve the working efficiency of the robot, and improve the quality of human life. For example, in some accident sites where the environment is harsh and it is difficult for humans to reach, good global path planning technology can enable the rescue robot to cross obstacles to reach the target location to carry out rescue tasks; in family life, the "eyes" and "ears" of the service robot can understand the home environment , from one r...

AI Technical Summary

Problems solved by technology

However, in many practical application scenarios, we cannot build high-quality global maps, and we do not even have the conditions to enter the scene in advance to build a global map

Therefore, a variety of limiting factors lead to a huge workload in the actual application of this technology, a sharp drop in the experience of human-computer interaction, the inability to complete tasks conveniently and quickly, and it is difficult to apply and promote a large number of them in actual scenarios

Images