GainAdaptor: Learning Quadrupedal Locomotion with Dual Actors for Adaptable and Energy-Efficient Walking on Various Terrains
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909425555472384 |
|---|---|
| author | Kim, Mincheol Kwon, Nahyun Kim, Jung-Yup |
| author_facet | Kim, Mincheol Kwon, Nahyun Kim, Jung-Yup |
| contents | Deep reinforcement learning (DRL) has emerged as an innovative solution for controlling legged robots in challenging environments using minimalist architectures. Traditional control methods for legged robots, such as inverse dynamics, either directly manage joint torques or use proportional-derivative (PD) controllers to regulate joint positions at a higher level. In case of DRL, direct torque control presents significant challenges, leading to a preference for joint position control. However, this approach necessitates careful adjustment of joint PD gains, which can limit both adaptability and efficiency. In this paper, we propose GainAdaptor, an adaptive gain control framework that autonomously tunes joint PD gains to enhance terrain adaptability and energy efficiency. The framework employs a dual-actor algorithm to dynamically adjust the PD gains based on varying ground conditions. By utilizing a divided action space, GainAdaptor efficiently learns stable and energy-efficient locomotion. We validate the effectiveness of the proposed method through experiments conducted on a Unitree Go1 robot, demonstrating improved locomotion performance across diverse terrains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09520 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GainAdaptor: Learning Quadrupedal Locomotion with Dual Actors for Adaptable and Energy-Efficient Walking on Various Terrains Kim, Mincheol Kwon, Nahyun Kim, Jung-Yup Robotics Machine Learning Deep reinforcement learning (DRL) has emerged as an innovative solution for controlling legged robots in challenging environments using minimalist architectures. Traditional control methods for legged robots, such as inverse dynamics, either directly manage joint torques or use proportional-derivative (PD) controllers to regulate joint positions at a higher level. In case of DRL, direct torque control presents significant challenges, leading to a preference for joint position control. However, this approach necessitates careful adjustment of joint PD gains, which can limit both adaptability and efficiency. In this paper, we propose GainAdaptor, an adaptive gain control framework that autonomously tunes joint PD gains to enhance terrain adaptability and energy efficiency. The framework employs a dual-actor algorithm to dynamically adjust the PD gains based on varying ground conditions. By utilizing a divided action space, GainAdaptor efficiently learns stable and energy-efficient locomotion. We validate the effectiveness of the proposed method through experiments conducted on a Unitree Go1 robot, demonstrating improved locomotion performance across diverse terrains. |
| title | GainAdaptor: Learning Quadrupedal Locomotion with Dual Actors for Adaptable and Energy-Efficient Walking on Various Terrains |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2412.09520 |