Learning Vision-Based Bipedal Locomotion for Challenging Terrain
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929414231556096 |
|---|---|
| author | Duan, Helei Pandit, Bikram Gadde, Mohitvishnu S. van Marum, Bart Dao, Jeremy Kim, Chanho Fern, Alan |
| author_facet | Duan, Helei Pandit, Bikram Gadde, Mohitvishnu S. van Marum, Bart Dao, Jeremy Kim, Chanho Fern, Alan |
| contents | Reinforcement learning (RL) for bipedal locomotion has recently demonstrated robust gaits over moderate terrains using only proprioceptive sensing. However, such blind controllers will fail in environments where robots must anticipate and adapt to local terrain, which requires visual perception. In this paper, we propose a fully-learned system that allows bipedal robots to react to local terrain while maintaining commanded travel speed and direction. Our approach first trains a controller in simulation using a heightmap expressed in the robot's local frame. Next, data is collected in simulation to train a heightmap predictor, whose input is the history of depth images and robot states. We demonstrate that with appropriate domain randomization, this approach allows for successful sim-to-real transfer with no explicit pose estimation and no fine-tuning using real-world data. To the best of our knowledge, this is the first example of sim-to-real learning for vision-based bipedal locomotion over challenging terrains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_14594 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning Vision-Based Bipedal Locomotion for Challenging Terrain Duan, Helei Pandit, Bikram Gadde, Mohitvishnu S. van Marum, Bart Dao, Jeremy Kim, Chanho Fern, Alan Robotics Reinforcement learning (RL) for bipedal locomotion has recently demonstrated robust gaits over moderate terrains using only proprioceptive sensing. However, such blind controllers will fail in environments where robots must anticipate and adapt to local terrain, which requires visual perception. In this paper, we propose a fully-learned system that allows bipedal robots to react to local terrain while maintaining commanded travel speed and direction. Our approach first trains a controller in simulation using a heightmap expressed in the robot's local frame. Next, data is collected in simulation to train a heightmap predictor, whose input is the history of depth images and robot states. We demonstrate that with appropriate domain randomization, this approach allows for successful sim-to-real transfer with no explicit pose estimation and no fine-tuning using real-world data. To the best of our knowledge, this is the first example of sim-to-real learning for vision-based bipedal locomotion over challenging terrains. |
| title | Learning Vision-Based Bipedal Locomotion for Challenging Terrain |
| topic | Robotics |
| url | https://arxiv.org/abs/2309.14594 |