Space Processor Computation Time Analysis for Reinforcement Learning and Run Time Assurance Control Policies
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913346579595264 |
|---|---|
| author | Dunlap, Kyle Hamilton, Nathaniel Viramontes, Francisco Landauer, Derrek Kain, Evan Hobbs, Kerianne L. |
| author_facet | Dunlap, Kyle Hamilton, Nathaniel Viramontes, Francisco Landauer, Derrek Kain, Evan Hobbs, Kerianne L. |
| contents | As the number of spacecraft on orbit continues to grow, it is challenging for human operators to constantly monitor and plan for all missions. Autonomous control methods such as reinforcement learning (RL) have the power to solve complex tasks while reducing the need for constant operator intervention. By combining RL solutions with run time assurance (RTA), safety of these systems can be assured in real time. However, in order to use these algorithms on board a spacecraft, they must be able to run in real time on space grade processors, which are typically outdated and less capable than state-of-the-art equipment. In this paper, multiple RL-trained neural network controllers (NNCs) and RTA algorithms were tested on commercial-off-the-shelf (COTS) and radiation tolerant processors. The results show that all NNCs and most RTA algorithms can compute optimal and safe actions in well under 1 second with room for further optimization before deploying in the real world. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06771 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Space Processor Computation Time Analysis for Reinforcement Learning and Run Time Assurance Control Policies Dunlap, Kyle Hamilton, Nathaniel Viramontes, Francisco Landauer, Derrek Kain, Evan Hobbs, Kerianne L. Systems and Control As the number of spacecraft on orbit continues to grow, it is challenging for human operators to constantly monitor and plan for all missions. Autonomous control methods such as reinforcement learning (RL) have the power to solve complex tasks while reducing the need for constant operator intervention. By combining RL solutions with run time assurance (RTA), safety of these systems can be assured in real time. However, in order to use these algorithms on board a spacecraft, they must be able to run in real time on space grade processors, which are typically outdated and less capable than state-of-the-art equipment. In this paper, multiple RL-trained neural network controllers (NNCs) and RTA algorithms were tested on commercial-off-the-shelf (COTS) and radiation tolerant processors. The results show that all NNCs and most RTA algorithms can compute optimal and safe actions in well under 1 second with room for further optimization before deploying in the real world. |
| title | Space Processor Computation Time Analysis for Reinforcement Learning and Run Time Assurance Control Policies |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2405.06771 |