The invention discloses a biped robot walking control method and electronic equipment based on an adversarial network, and the method comprises the steps: S1, collecting multiple groups of data of a biped robot, wherein each group of data comprising state data, action data and state data after action; S2, inputting the data acquired in the step S1 into an adversarial network for training; and S3, controlling the biped robot to walk according to the action data output by the trained adversarial network. According to the method, an unsupervised neural network optimization algorithm (adversarial network) is adopted, an optimal dynamic model of the robot can be obtained under the mutual game of a generator and a discriminator, and an intelligent swarm search optimization algorithm (particle swarm optimization algorithm) is adopted, so that optimal action parameters can be obtained.
本发明公开了一种基于对抗网络的双足机器人行走控制方法及电子设备,包括:S1采集双足机器人的多组数据,每一组数据包括状态数据、动作数据、动作之后的状态数据;S2将步骤S1采集的数据输入对抗网络进行训练;S3控制双足机器人按照训练好的对抗网络输出的动作数据进行行走。本发明采用一种无监督的神经网络优化算法(对抗网络),能够在生成器与鉴别器的相互博弈下得到机器人的最佳动力学模型,并且采用一种智能的群搜索优化算法(粒子群优化算法),能够得到最优的动作参数。
Biped robot walking control method based on adversarial network and electronic equipment
一种基于对抗网络的双足机器人行走控制方法及电子设备
2021-07-23
Patent
Electronic Resource
Chinese
IPC: | G05D SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES , Systeme zum Steuern oder Regeln nichtelektrischer veränderlicher Größen / B62D MOTOR VEHICLES , Motorfahrzeuge / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Biped walking robot control method and biped walking robot control system
European Patent Office | 2016
|WALKING CONTROL METHOD, WALKING CONTROL PROGRAM AND BIPED WALKING ROBOT
European Patent Office | 2017
|Biped robot walking control method and device and electronic equipment
European Patent Office | 2024
|Walking control method, walking control program and biped walking robot
European Patent Office | 2019
|