A Gait Driven Reinforcement Learning Framework for Humanoid Robots
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914300021440512 |
|---|---|
| author | Li, Bolin Jiang, Yuzhi Sun, Linwei Huang, Xuecong Zhu, Lijun Ding, Han |
| author_facet | Li, Bolin Jiang, Yuzhi Sun, Linwei Huang, Xuecong Zhu, Lijun Ding, Han |
| contents | This paper presents a real-time gait driven training framework for humanoid robots. First, we introduce a novel gait planner that incorporates dynamics to design the desired joint trajectory. In the gait design process, the 3D robot model is decoupled into two 2D models, which are then approximated as hybrid inverted pendulums (H-LIP) for trajectory planning. The gait planner operates in parallel in real time within the robot's learning environment. Second, based on this gait planner, we design three effective reward functions within a reinforcement learning framework, forming a reward composition to achieve periodic bipedal gait. This reward composition reduces the robot's learning time and enhances locomotion performance. Finally, a gait design example, along with simulation and experimental comparisons, is presented to demonstrate the effectiveness of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08416 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Gait Driven Reinforcement Learning Framework for Humanoid Robots Li, Bolin Jiang, Yuzhi Sun, Linwei Huang, Xuecong Zhu, Lijun Ding, Han Robotics This paper presents a real-time gait driven training framework for humanoid robots. First, we introduce a novel gait planner that incorporates dynamics to design the desired joint trajectory. In the gait design process, the 3D robot model is decoupled into two 2D models, which are then approximated as hybrid inverted pendulums (H-LIP) for trajectory planning. The gait planner operates in parallel in real time within the robot's learning environment. Second, based on this gait planner, we design three effective reward functions within a reinforcement learning framework, forming a reward composition to achieve periodic bipedal gait. This reward composition reduces the robot's learning time and enhances locomotion performance. Finally, a gait design example, along with simulation and experimental comparisons, is presented to demonstrate the effectiveness of the proposed method. |
| title | A Gait Driven Reinforcement Learning Framework for Humanoid Robots |
| topic | Robotics |
| url | https://arxiv.org/abs/2506.08416 |