Humanoid robot motion control method and system based on deep reinforcement learning

Abstract

The invention discloses a humanoid robot motion control method and system based on deep reinforcement learning. The method comprises the steps that S1, simulation control is carried out, specifically,the current state of a humanoid robot is obtained, and the target angle of each joint of the humanoid robot are calculated and determined through a preset deep reinforcement learning model accordingto the current state; and S2, PD control is carried out, specifically, through a PD controller, the target angle serves as a control target, the actual angle and the joint torque of the joint serve asfeedback, the control torque of the joint is determined, and the joint is controlled to act according to the control torque. The method has the advantages of good control stability, good reliabilityand the like.

Description

technical field [0001] The invention relates to the technical field of motion control of humanoid robots, in particular to a method and system for motion control of humanoid robots based on deep reinforcement learning. Background technique [0002] Humanoid robots have great application potential and can be deployed in environments where the use of wheeled robots is limited, such as terrain with obstacles, narrow and elevated surfaces (such as stairs). However, compared with wheeled or tracked robots, humanoid robots are inherently unstable and require active control to achieve equilibrium due to their limited support area, high center of mass, and limited actuator capabilities. Therefore, the range of application scenarios for humanoid robots is mainly limited by the ability of humanoid robots to maintain balance and cope with disturbances and uncertainties. [0003] Classical control methods propose a variety of motion algorithms, but these algorithms lack versatility, an...

AI Technical Summary

Problems solved by technology

However, compared with wheeled or tracked robots, humanoid robots are inherently unstable and require active control to achieve equilibrium due to their limited support area, high center of mass, and limited actuator capabilities

Therefore, the scope of application scenarios of humanoid robots is mainly limited by the balance of humanoid robots and the ability to deal with disturbances and uncertainties.

[0003] Classical control methods propose a variety of motion algorithms, but these algorithms lack versatility and are trained based on simplified models, which have poor anti-interference ability

In recent years, reinforcement learning algorithms have been applied to the motion control of humanoid robots, but there are still problems such as difficulty in parameter adjustment and slow training, and it is difficult to achieve stable and reliable motion control of humanoid robots

Images