DiPPeR: Diffusion-based 2D Path Planner applied on Legged Robots
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911891467534336 |
|---|---|
| author | Liu, Jianwei Stamatopoulou, Maria Kanoulas, Dimitrios |
| author_facet | Liu, Jianwei Stamatopoulou, Maria Kanoulas, Dimitrios |
| contents | In this work, we present DiPPeR, a novel and fast 2D path planning framework for quadrupedal locomotion, leveraging diffusion-driven techniques. Our contributions include a scalable dataset generator for map images and corresponding trajectories, an image-conditioned diffusion planner for mobile robots, and a training/inference pipeline employing CNNs. We validate our approach in several mazes, as well as in real-world deployment scenarios on Boston Dynamic's Spot and Unitree's Go1 robots. DiPPeR performs on average 23 times faster for trajectory generation against both search based and data driven path planning algorithms with an average of 87% consistency in producing feasible paths of various length in maps of variable size, and obstacle structure. Website: https://rpl-cs-ucl.github.io/DiPPeR |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_07842 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DiPPeR: Diffusion-based 2D Path Planner applied on Legged Robots Liu, Jianwei Stamatopoulou, Maria Kanoulas, Dimitrios Robotics In this work, we present DiPPeR, a novel and fast 2D path planning framework for quadrupedal locomotion, leveraging diffusion-driven techniques. Our contributions include a scalable dataset generator for map images and corresponding trajectories, an image-conditioned diffusion planner for mobile robots, and a training/inference pipeline employing CNNs. We validate our approach in several mazes, as well as in real-world deployment scenarios on Boston Dynamic's Spot and Unitree's Go1 robots. DiPPeR performs on average 23 times faster for trajectory generation against both search based and data driven path planning algorithms with an average of 87% consistency in producing feasible paths of various length in maps of variable size, and obstacle structure. Website: https://rpl-cs-ucl.github.io/DiPPeR |
| title | DiPPeR: Diffusion-based 2D Path Planner applied on Legged Robots |
| topic | Robotics |
| url | https://arxiv.org/abs/2310.07842 |