Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909574735331328 |
|---|---|
| author | Katayama, Sotaro Koda, Yuta Nagatsuka, Norio Kinoshita, Masaya |
| author_facet | Katayama, Sotaro Koda, Yuta Nagatsuka, Norio Kinoshita, Masaya |
| contents | Sim-to-real reinforcement learning (RL) for humanoid robots with high-gear ratio actuators remains challenging due to complex actuator dynamics and the absence of torque sensors. To address this, we propose a novel RL framework leveraging foot-mounted inertial measurement units (IMUs). Instead of pursuing detailed actuator modeling and system identification, we utilize foot-mounted IMU measurements to enhance rapid stabilization capabilities over challenging terrains. Additionally, we propose symmetric data augmentation dedicated to the proposed observation space and random network distillation to enhance bipedal locomotion learning over rough terrain. We validate our approach through hardware experiments on a miniature-sized humanoid EVAL-03 over a variety of environments. The experimental results demonstrate that our method improves rapid stabilization capabilities over non-rigid surfaces and sudden environmental transitions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00614 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs Katayama, Sotaro Koda, Yuta Nagatsuka, Norio Kinoshita, Masaya Robotics Sim-to-real reinforcement learning (RL) for humanoid robots with high-gear ratio actuators remains challenging due to complex actuator dynamics and the absence of torque sensors. To address this, we propose a novel RL framework leveraging foot-mounted inertial measurement units (IMUs). Instead of pursuing detailed actuator modeling and system identification, we utilize foot-mounted IMU measurements to enhance rapid stabilization capabilities over challenging terrains. Additionally, we propose symmetric data augmentation dedicated to the proposed observation space and random network distillation to enhance bipedal locomotion learning over rough terrain. We validate our approach through hardware experiments on a miniature-sized humanoid EVAL-03 over a variety of environments. The experimental results demonstrate that our method improves rapid stabilization capabilities over non-rigid surfaces and sudden environmental transitions. |
| title | Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs |
| topic | Robotics |
| url | https://arxiv.org/abs/2504.00614 |