Humanoid Robot Walking and Grasping Method Using Similarity Reward-Augmented Generative Adversarial Imitation Learning

This study aims to enhance the precision of humanoid robots in imitating complex human “walking–grasping” coordinated movements. Addressing limitations in sample efficiency and reward function design in Generative Adversarial Imitation Learning (GAIL), we propose the Similarity Reward-Augmented Gene...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Gen-Yong Huang, Wen-Feng Li
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2026-04-01
Schriftenreihe:	Sensors
Schlagworte:	humanoid robot generative adversarial imitation learning similarity reward walking-grasping coordination maximum entropy reinforcement learning
Online-Zugang:	https://www.mdpi.com/1424-8220/26/9/2756
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!