Salvato in:
Dettagli Bibliografici
Autori principali: Ates, Yusuf Baran, Morgul, Omer
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.17387
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911278841200640
author Ates, Yusuf Baran
Morgul, Omer
author_facet Ates, Yusuf Baran
Morgul, Omer
contents Learning human-like, robust bipedal walking remains difficult due to hybrid dynamics and terrain variability. We propose a lightweight framework that combines a gait generator network learned from human motion with Proximal Policy Optimization (PPO) controller for torque control. Despite being trained only on flat or mildly sloped ground, the learned policies generalize to steeper ramps and rough surfaces. Results suggest that pairing spectral motion priors with Deep Reinforcement Learning (DRL) offers a practical path toward natural and robust bipedal locomotion with modest training cost.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17387
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human Imitated Bipedal Locomotion with Frequency Based Gait Generator Network
Ates, Yusuf Baran
Morgul, Omer
Robotics
Learning human-like, robust bipedal walking remains difficult due to hybrid dynamics and terrain variability. We propose a lightweight framework that combines a gait generator network learned from human motion with Proximal Policy Optimization (PPO) controller for torque control. Despite being trained only on flat or mildly sloped ground, the learned policies generalize to steeper ramps and rough surfaces. Results suggest that pairing spectral motion priors with Deep Reinforcement Learning (DRL) offers a practical path toward natural and robust bipedal locomotion with modest training cost.
title Human Imitated Bipedal Locomotion with Frequency Based Gait Generator Network
topic Robotics
url https://arxiv.org/abs/2511.17387