Abstract
Computational intelligence techniques have been used in a wide range of application areas. This paper proposes a new learning algorithm that dynamically shapes the landing trajectories, based on potential function methods, in order to provide computationally efficient on-board guidance and control. Extreme Learning Machine (ELM) devises a Single Layer Forward Network (SLFN) to learn the relationship between the current spacecraft position and the optimal velocity field. The SLFN design is tested and validated on a set of data comprising data points belonging to the training set on which the network has not been trained. Furthermore, the proposed efficient algorithm is tested in typical simulation scenarios which include a set of Monte Carlo simulation to evaluate the guidance performances
Original language | English |
---|---|
Pages | AAS 15-356 |
Number of pages | 19 |
Publication status | Published - 11 Jan 2015 |
Event | 25th AAS/AIAA Space Flight Mechanics Meeting - Willliamsburg, VA, United States Duration: 11 Jan 2015 → 15 Jan 2015 |
Conference
Conference | 25th AAS/AIAA Space Flight Mechanics Meeting |
---|---|
Country | United States |
City | Willliamsburg, VA |
Period | 11/01/15 → 15/01/15 |
Keywords
- performance evaluation
- artificial neural network
- algorithm design and analysis
- guidance control systems
- ELMS