CusADi: A GPU Parallelization Framework for Symbolic Expressions and Optimal Control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913471255281664 |
|---|---|
| author | Jeon, Se Hwan Hong, Seungwoo Lee, Ho Jae Khazoom, Charles Kim, Sangbae |
| author_facet | Jeon, Se Hwan Hong, Seungwoo Lee, Ho Jae Khazoom, Charles Kim, Sangbae |
| contents | The parallelism afforded by GPUs presents significant advantages in training controllers through reinforcement learning (RL). However, integrating model-based optimization into this process remains challenging due to the complexity of formulating and solving optimization problems across thousands of instances. In this work, we present CusADi, an extension of the CasADi symbolic framework to support the parallelization of arbitrary closed-form expressions on GPUs with CUDA. We also formulate a closed-form approximation for solving general optimal control problems, enabling large-scale parallelization and evaluation of MPC controllers. Our results show a ten-fold speedup relative to similar MPC implementation on the CPU, and we demonstrate the use of CusADi for various applications, including parallel simulation, parameter sweeps, and policy training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09662 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CusADi: A GPU Parallelization Framework for Symbolic Expressions and Optimal Control Jeon, Se Hwan Hong, Seungwoo Lee, Ho Jae Khazoom, Charles Kim, Sangbae Robotics Distributed, Parallel, and Cluster Computing The parallelism afforded by GPUs presents significant advantages in training controllers through reinforcement learning (RL). However, integrating model-based optimization into this process remains challenging due to the complexity of formulating and solving optimization problems across thousands of instances. In this work, we present CusADi, an extension of the CasADi symbolic framework to support the parallelization of arbitrary closed-form expressions on GPUs with CUDA. We also formulate a closed-form approximation for solving general optimal control problems, enabling large-scale parallelization and evaluation of MPC controllers. Our results show a ten-fold speedup relative to similar MPC implementation on the CPU, and we demonstrate the use of CusADi for various applications, including parallel simulation, parameter sweeps, and policy training. |
| title | CusADi: A GPU Parallelization Framework for Symbolic Expressions and Optimal Control |
| topic | Robotics Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2408.09662 |