MPPI-Generic: A CUDA Library for Stochastic Trajectory Optimization
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_ | 1866912924398780416 |
|---|---|
| author | Vlahov, Bogdan Gibson, Jason Gandhi, Manan Theodorou, Evangelos A. |
| author_facet | Vlahov, Bogdan Gibson, Jason Gandhi, Manan Theodorou, Evangelos A. |
| contents | This paper introduces a new C++/CUDA library for GPU-accelerated stochastic optimization called MPPI-Generic. It provides implementations of Model Predictive Path Integral control, Tube-Model Predictive Path Integral Control, and Robust Model Predictive Path Integral Control, and allows for these algorithms to be used across many pre-existing dynamics models and cost functions. Furthermore, researchers can create their own dynamics models or cost functions following our API definitions without needing to change the actual Model Predictive Path Integral Control code. Finally, we compare computational performance to other popular implementations of Model Predictive Path Integral Control over a variety of GPUs to show the real-time capabilities our library can allow for. Library code can be found at: https://acdslab.github.io/mppi-generic-website/ . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07563 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MPPI-Generic: A CUDA Library for Stochastic Trajectory Optimization Vlahov, Bogdan Gibson, Jason Gandhi, Manan Theodorou, Evangelos A. Mathematical Software Distributed, Parallel, and Cluster Computing Robotics Systems and Control This paper introduces a new C++/CUDA library for GPU-accelerated stochastic optimization called MPPI-Generic. It provides implementations of Model Predictive Path Integral control, Tube-Model Predictive Path Integral Control, and Robust Model Predictive Path Integral Control, and allows for these algorithms to be used across many pre-existing dynamics models and cost functions. Furthermore, researchers can create their own dynamics models or cost functions following our API definitions without needing to change the actual Model Predictive Path Integral Control code. Finally, we compare computational performance to other popular implementations of Model Predictive Path Integral Control over a variety of GPUs to show the real-time capabilities our library can allow for. Library code can be found at: https://acdslab.github.io/mppi-generic-website/ . |
| title | MPPI-Generic: A CUDA Library for Stochastic Trajectory Optimization |
| topic | Mathematical Software Distributed, Parallel, and Cluster Computing Robotics Systems and Control |
| url | https://arxiv.org/abs/2409.07563 |