Optimal Abort Guidance and Experimental Verification Based on Feature LearningSource: Journal of Aerospace Engineering:;2024:;Volume ( 037 ):;issue: 002::page 04023124-1Author:Vinay Kenny
,
Sixiong You
,
Chaoying Pei
,
Godfrey Hendrix
,
Roha Gul
,
Ran Dai
,
Jeremy Rea
DOI: 10.1061/JAEEEZ.ASENG-5030Publisher: ASCE
Abstract: The abort mission refers to the mission where the landing vehicle needs to terminate the landing mission when an anomaly happens and be safely guided to the desired orbit. This paper focuses on solving the time-optimal abort guidance (TOAG) problem in real-time via the feature-based learning method. First, according to the optimal control theory, the features are identified to represent the optimal solutions of TOAG using a few parameters. After that, a sufficiently large data set of time-optimal abort trajectories is generated offline by solving the TOAG problems with different initial conditions. Then, the features are extracted for all generated cases. To find the implicit relationships between the initial conditions and identified features, neural networks are constructed to map the relationships based on the generated data set. Finally, experimental flight tests are conducted to demonstrate the onboard computation capability and effectiveness of the proposed method.
|
Collections
Show full item record
| contributor author | Vinay Kenny | |
| contributor author | Sixiong You | |
| contributor author | Chaoying Pei | |
| contributor author | Godfrey Hendrix | |
| contributor author | Roha Gul | |
| contributor author | Ran Dai | |
| contributor author | Jeremy Rea | |
| date accessioned | 2024-04-27T22:39:21Z | |
| date available | 2024-04-27T22:39:21Z | |
| date issued | 2024/03/01 | |
| identifier other | 10.1061-JAEEEZ.ASENG-5030.pdf | |
| identifier uri | http://yetl.yabesh.ir/yetl1/handle/yetl/4297179 | |
| description abstract | The abort mission refers to the mission where the landing vehicle needs to terminate the landing mission when an anomaly happens and be safely guided to the desired orbit. This paper focuses on solving the time-optimal abort guidance (TOAG) problem in real-time via the feature-based learning method. First, according to the optimal control theory, the features are identified to represent the optimal solutions of TOAG using a few parameters. After that, a sufficiently large data set of time-optimal abort trajectories is generated offline by solving the TOAG problems with different initial conditions. Then, the features are extracted for all generated cases. To find the implicit relationships between the initial conditions and identified features, neural networks are constructed to map the relationships based on the generated data set. Finally, experimental flight tests are conducted to demonstrate the onboard computation capability and effectiveness of the proposed method. | |
| publisher | ASCE | |
| title | Optimal Abort Guidance and Experimental Verification Based on Feature Learning | |
| type | Journal Article | |
| journal volume | 37 | |
| journal issue | 2 | |
| journal title | Journal of Aerospace Engineering | |
| identifier doi | 10.1061/JAEEEZ.ASENG-5030 | |
| journal fristpage | 04023124-1 | |
| journal lastpage | 04023124-15 | |
| page | 15 | |
| tree | Journal of Aerospace Engineering:;2024:;Volume ( 037 ):;issue: 002 | |
| contenttype | Fulltext |