Learning Quiet Walking for a Small Home Robot
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929735188086784 |
|---|---|
| author | Watanabe, Ryo Miki, Takahiro Shi, Fan Kadokawa, Yuki Bjelonic, Filip Kawaharazuka, Kento Cramariuc, Andrei Hutter, Marco |
| author_facet | Watanabe, Ryo Miki, Takahiro Shi, Fan Kadokawa, Yuki Bjelonic, Filip Kawaharazuka, Kento Cramariuc, Andrei Hutter, Marco |
| contents | As home robotics gains traction, robots are increasingly integrated into households, offering companionship and assistance. Quadruped robots, particularly those resembling dogs, have emerged as popular alternatives for traditional pets. However, user feedback highlights concerns about the noise these robots generate during walking at home, particularly the loud footstep sound. To address this issue, we propose a sim-to-real based reinforcement learning (RL) approach to minimize the foot contact velocity highly related to the footstep sound. Our framework incorporates three key elements: learning varying PD gains to actively dampen and stiffen each joint, utilizing foot contact sensors, and employing curriculum learning to gradually enforce penalties on foot contact velocity. Experiments demonstrate that our learned policy achieves superior quietness compared to a RL baseline and the carefully handcrafted Sony commercial controllers. Furthermore, the trade-off between robustness and quietness is shown. This research contributes to developing quieter and more user-friendly robotic companions in home environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10983 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Quiet Walking for a Small Home Robot Watanabe, Ryo Miki, Takahiro Shi, Fan Kadokawa, Yuki Bjelonic, Filip Kawaharazuka, Kento Cramariuc, Andrei Hutter, Marco Robotics As home robotics gains traction, robots are increasingly integrated into households, offering companionship and assistance. Quadruped robots, particularly those resembling dogs, have emerged as popular alternatives for traditional pets. However, user feedback highlights concerns about the noise these robots generate during walking at home, particularly the loud footstep sound. To address this issue, we propose a sim-to-real based reinforcement learning (RL) approach to minimize the foot contact velocity highly related to the footstep sound. Our framework incorporates three key elements: learning varying PD gains to actively dampen and stiffen each joint, utilizing foot contact sensors, and employing curriculum learning to gradually enforce penalties on foot contact velocity. Experiments demonstrate that our learned policy achieves superior quietness compared to a RL baseline and the carefully handcrafted Sony commercial controllers. Furthermore, the trade-off between robustness and quietness is shown. This research contributes to developing quieter and more user-friendly robotic companions in home environments. |
| title | Learning Quiet Walking for a Small Home Robot |
| topic | Robotics |
| url | https://arxiv.org/abs/2502.10983 |