Quadruped robot traversing 3D complex environments with limited perception
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_ | 1866910526270865408 |
|---|---|
| author | Cheng, Yi Liu, Hang Pan, Guoping Ye, Linqi Liu, Houde Liang, Bin |
| author_facet | Cheng, Yi Liu, Hang Pan, Guoping Ye, Linqi Liu, Houde Liang, Bin |
| contents | Traversing 3-D complex environments has always been a significant challenge for legged locomotion. Existing methods typically rely on external sensors such as vision and lidar to preemptively react to obstacles by acquiring environmental information. However, in scenarios like nighttime or dense forests, external sensors often fail to function properly, necessitating robots to rely on proprioceptive sensors to perceive diverse obstacles in the environment and respond promptly. This task is undeniably challenging. Our research finds that methods based on collision detection can enhance a robot's perception of environmental obstacles. In this work, we propose an end-to-end learning-based quadruped robot motion controller that relies solely on proprioceptive sensing. This controller can accurately detect, localize, and agilely respond to collisions in unknown and complex 3D environments, thereby improving the robot's traversability in complex environments. We demonstrate in both simulation and real-world experiments that our method enables quadruped robots to successfully traverse challenging obstacles in various complex environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18225 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quadruped robot traversing 3D complex environments with limited perception Cheng, Yi Liu, Hang Pan, Guoping Ye, Linqi Liu, Houde Liang, Bin Robotics Traversing 3-D complex environments has always been a significant challenge for legged locomotion. Existing methods typically rely on external sensors such as vision and lidar to preemptively react to obstacles by acquiring environmental information. However, in scenarios like nighttime or dense forests, external sensors often fail to function properly, necessitating robots to rely on proprioceptive sensors to perceive diverse obstacles in the environment and respond promptly. This task is undeniably challenging. Our research finds that methods based on collision detection can enhance a robot's perception of environmental obstacles. In this work, we propose an end-to-end learning-based quadruped robot motion controller that relies solely on proprioceptive sensing. This controller can accurately detect, localize, and agilely respond to collisions in unknown and complex 3D environments, thereby improving the robot's traversability in complex environments. We demonstrate in both simulation and real-world experiments that our method enables quadruped robots to successfully traverse challenging obstacles in various complex environments. |
| title | Quadruped robot traversing 3D complex environments with limited perception |
| topic | Robotics |
| url | https://arxiv.org/abs/2404.18225 |