Learning Barrier-Certified Polynomial Dynamical Systems for Obstacle Avoidance with Robots
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913463887986688 |
|---|---|
| author | Schonger, Martin Kussaba, Hugo T. M. Chen, Lingyun Figueredo, Luis Swikir, Abdalla Billard, Aude Haddadin, Sami |
| author_facet | Schonger, Martin Kussaba, Hugo T. M. Chen, Lingyun Figueredo, Luis Swikir, Abdalla Billard, Aude Haddadin, Sami |
| contents | Established techniques that enable robots to learn from demonstrations are based on learning a stable dynamical system (DS). To increase the robots' resilience to perturbations during tasks that involve static obstacle avoidance, we propose incorporating barrier certificates into an optimization problem to learn a stable and barrier-certified DS. Such optimization problem can be very complex or extremely conservative when the traditional linear parameter-varying formulation is used. Thus, different from previous approaches in the literature, we propose to use polynomial representations for DSs, which yields an optimization problem that can be tackled by sum-of-squares techniques. Finally, our approach can handle obstacle shapes that fall outside the scope of assumptions typically found in the literature concerning obstacle avoidance within the DS learning framework. Supplementary material can be found at the project webpage: https://martinschonger.github.io/abc-ds |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08178 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Barrier-Certified Polynomial Dynamical Systems for Obstacle Avoidance with Robots Schonger, Martin Kussaba, Hugo T. M. Chen, Lingyun Figueredo, Luis Swikir, Abdalla Billard, Aude Haddadin, Sami Robotics Systems and Control 68T40 I.2.9 Established techniques that enable robots to learn from demonstrations are based on learning a stable dynamical system (DS). To increase the robots' resilience to perturbations during tasks that involve static obstacle avoidance, we propose incorporating barrier certificates into an optimization problem to learn a stable and barrier-certified DS. Such optimization problem can be very complex or extremely conservative when the traditional linear parameter-varying formulation is used. Thus, different from previous approaches in the literature, we propose to use polynomial representations for DSs, which yields an optimization problem that can be tackled by sum-of-squares techniques. Finally, our approach can handle obstacle shapes that fall outside the scope of assumptions typically found in the literature concerning obstacle avoidance within the DS learning framework. Supplementary material can be found at the project webpage: https://martinschonger.github.io/abc-ds |
| title | Learning Barrier-Certified Polynomial Dynamical Systems for Obstacle Avoidance with Robots |
| topic | Robotics Systems and Control 68T40 I.2.9 |
| url | https://arxiv.org/abs/2403.08178 |