Modeling Irregular Small Bodies Gravity Field Via Extreme Learning Machines and Bayesian Optimization
Close proximity operations around small bodies are extremely challenging due to their uncertain dynamical environment. Autonomous guidance and navigation around small bodies require fast and accurate modeling of the gravitational field for potential on-board computation. In this paper, we investigat...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2021
|
| Online Access: | https://hdl.handle.net/1721.1/134439 |
| _version_ | 1826201885416095744 |
|---|---|
| author | Furfaro, Roberto Barocco, Riccardo Linares, Richard Topputo, Francesco Reddy, Vishnu Simo, Jules Le Corre, Lucille |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Furfaro, Roberto Barocco, Riccardo Linares, Richard Topputo, Francesco Reddy, Vishnu Simo, Jules Le Corre, Lucille |
| author_sort | Furfaro, Roberto |
| collection | MIT |
| description | Close proximity operations around small bodies are extremely challenging due to their uncertain dynamical environment. Autonomous guidance and navigation around small bodies require fast and accurate modeling of the gravitational field for potential on-board computation. In this paper, we investigate a model-based, data-driven approach to compute and predict the gravitational acceleration around irregular small bodies. More specifically, we employ Extreme Learning Machine (ELM) theories to design, train and validate Single-Layer Feedforward Networks (SLFN) capable of learning the relationship between the spacecraft position and the gravitational acceleration. ELM-base neural networks are trained without iterative tuning therefore dramatically reducing the training time. Analysis of performance in constant density models for asteroid 25143 Itokawa and comet 67/P Churyumov-Gerasimenko show that ELM-based SLFN are able learn the desired functional relationship both globally and in selected localized areas near the surface. The latter results in a robust neural algorithm for on-board, real-time calculation of the gravity field needed for guidance and control in close-proximity operations near the asteroid surface. |
| first_indexed | 2024-09-23T11:58:25Z |
| format | Article |
| id | mit-1721.1/134439 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:58:25Z |
| publishDate | 2021 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1344392023-12-06T18:43:39Z Modeling Irregular Small Bodies Gravity Field Via Extreme Learning Machines and Bayesian Optimization Furfaro, Roberto Barocco, Riccardo Linares, Richard Topputo, Francesco Reddy, Vishnu Simo, Jules Le Corre, Lucille Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Close proximity operations around small bodies are extremely challenging due to their uncertain dynamical environment. Autonomous guidance and navigation around small bodies require fast and accurate modeling of the gravitational field for potential on-board computation. In this paper, we investigate a model-based, data-driven approach to compute and predict the gravitational acceleration around irregular small bodies. More specifically, we employ Extreme Learning Machine (ELM) theories to design, train and validate Single-Layer Feedforward Networks (SLFN) capable of learning the relationship between the spacecraft position and the gravitational acceleration. ELM-base neural networks are trained without iterative tuning therefore dramatically reducing the training time. Analysis of performance in constant density models for asteroid 25143 Itokawa and comet 67/P Churyumov-Gerasimenko show that ELM-based SLFN are able learn the desired functional relationship both globally and in selected localized areas near the surface. The latter results in a robust neural algorithm for on-board, real-time calculation of the gravity field needed for guidance and control in close-proximity operations near the asteroid surface. 2021-10-27T20:05:01Z 2021-10-27T20:05:01Z 2021 2021-05-06T12:47:14Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/134439 en 10.1016/J.ASR.2020.06.021 Advances in Space Research Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV Other repository |
| spellingShingle | Furfaro, Roberto Barocco, Riccardo Linares, Richard Topputo, Francesco Reddy, Vishnu Simo, Jules Le Corre, Lucille Modeling Irregular Small Bodies Gravity Field Via Extreme Learning Machines and Bayesian Optimization |
| title | Modeling Irregular Small Bodies Gravity Field Via Extreme Learning Machines and Bayesian Optimization |
| title_full | Modeling Irregular Small Bodies Gravity Field Via Extreme Learning Machines and Bayesian Optimization |
| title_fullStr | Modeling Irregular Small Bodies Gravity Field Via Extreme Learning Machines and Bayesian Optimization |
| title_full_unstemmed | Modeling Irregular Small Bodies Gravity Field Via Extreme Learning Machines and Bayesian Optimization |
| title_short | Modeling Irregular Small Bodies Gravity Field Via Extreme Learning Machines and Bayesian Optimization |
| title_sort | modeling irregular small bodies gravity field via extreme learning machines and bayesian optimization |
| url | https://hdl.handle.net/1721.1/134439 |
| work_keys_str_mv | AT furfaroroberto modelingirregularsmallbodiesgravityfieldviaextremelearningmachinesandbayesianoptimization AT baroccoriccardo modelingirregularsmallbodiesgravityfieldviaextremelearningmachinesandbayesianoptimization AT linaresrichard modelingirregularsmallbodiesgravityfieldviaextremelearningmachinesandbayesianoptimization AT topputofrancesco modelingirregularsmallbodiesgravityfieldviaextremelearningmachinesandbayesianoptimization AT reddyvishnu modelingirregularsmallbodiesgravityfieldviaextremelearningmachinesandbayesianoptimization AT simojules modelingirregularsmallbodiesgravityfieldviaextremelearningmachinesandbayesianoptimization AT lecorrelucille modelingirregularsmallbodiesgravityfieldviaextremelearningmachinesandbayesianoptimization |