Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control
In this paper, we present a novel guidance scheme based on model-based deep reinforcement learning (RL) technique. With model-based deep RL method, a deep neural network is trained as a predictive model of guidance dynamics which is incorporated into a model predictive path integral (MPPI) control f...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8682051/ |
| _version_ | 1819276091229995008 |
|---|---|
| author | Chen Liang Weihong Wang Zhenghua Liu Chao Lai Benchun Zhou |
| author_facet | Chen Liang Weihong Wang Zhenghua Liu Chao Lai Benchun Zhou |
| author_sort | Chen Liang |
| collection | DOAJ |
| description | In this paper, we present a novel guidance scheme based on model-based deep reinforcement learning (RL) technique. With model-based deep RL method, a deep neural network is trained as a predictive model of guidance dynamics which is incorporated into a model predictive path integral (MPPI) control framework. However, the traditional MPPI framework assumes the actual environment similar to the training dataset for the deep neural network which is impractical in practice with different maneuvering of the target, other perturbations, and actuator failures. To address this problem, our method utilizes meta-learning technique to make the deep neural dynamics model adapt to such changes online. With this approach, we can alleviate the performance deterioration of standard MPPI control caused by the difference between the actual environment and training data. Then, a novel guidance law for a varying velocity interceptor intercepting maneuvering target with desired terminal impact angle under actuator failure is constructed based on the aforementioned techniques. The simulation and experiment results under different cases show the effectiveness and robustness of the proposed guidance law in achieving successful interceptions of maneuvering target. |
| first_indexed | 2024-12-23T23:34:42Z |
| format | Article |
| id | doaj.art-b1f68edf997e48c4a102079545bb0894 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-23T23:34:42Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b1f68edf997e48c4a102079545bb08942022-12-21T17:25:54ZengIEEEIEEE Access2169-35362019-01-017473534736510.1109/ACCESS.2019.29095798682051Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral ControlChen Liang0https://orcid.org/0000-0002-1991-7586Weihong Wang1Zhenghua Liu2Chao Lai3https://orcid.org/0000-0003-2758-4125Benchun Zhou4School of Automation Science and Electrical Engineering, Beihang University, Beijing, ChinaSchool of Automation Science and Electrical Engineering, Beihang University, Beijing, ChinaSchool of Automation Science and Electrical Engineering, Beihang University, Beijing, ChinaNavigation and Control Technology Research Institute, China North Industries Group Corporation, Beijing, ChinaSchool of Automation Science and Electrical Engineering, Beihang University, Beijing, ChinaIn this paper, we present a novel guidance scheme based on model-based deep reinforcement learning (RL) technique. With model-based deep RL method, a deep neural network is trained as a predictive model of guidance dynamics which is incorporated into a model predictive path integral (MPPI) control framework. However, the traditional MPPI framework assumes the actual environment similar to the training dataset for the deep neural network which is impractical in practice with different maneuvering of the target, other perturbations, and actuator failures. To address this problem, our method utilizes meta-learning technique to make the deep neural dynamics model adapt to such changes online. With this approach, we can alleviate the performance deterioration of standard MPPI control caused by the difference between the actual environment and training data. Then, a novel guidance law for a varying velocity interceptor intercepting maneuvering target with desired terminal impact angle under actuator failure is constructed based on the aforementioned techniques. The simulation and experiment results under different cases show the effectiveness and robustness of the proposed guidance law in achieving successful interceptions of maneuvering target.https://ieeexplore.ieee.org/document/8682051/Missile guidancemodel predictive controlmeta-learningdeep reinforcement learningimpact angle constraint |
| spellingShingle | Chen Liang Weihong Wang Zhenghua Liu Chao Lai Benchun Zhou Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control IEEE Access Missile guidance model predictive control meta-learning deep reinforcement learning impact angle constraint |
| title | Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control |
| title_full | Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control |
| title_fullStr | Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control |
| title_full_unstemmed | Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control |
| title_short | Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control |
| title_sort | learning to guide guidance law based on deep meta learning and model predictive path integral control |
| topic | Missile guidance model predictive control meta-learning deep reinforcement learning impact angle constraint |
| url | https://ieeexplore.ieee.org/document/8682051/ |
| work_keys_str_mv | AT chenliang learningtoguideguidancelawbasedondeepmetalearningandmodelpredictivepathintegralcontrol AT weihongwang learningtoguideguidancelawbasedondeepmetalearningandmodelpredictivepathintegralcontrol AT zhenghualiu learningtoguideguidancelawbasedondeepmetalearningandmodelpredictivepathintegralcontrol AT chaolai learningtoguideguidancelawbasedondeepmetalearningandmodelpredictivepathintegralcontrol AT benchunzhou learningtoguideguidancelawbasedondeepmetalearningandmodelpredictivepathintegralcontrol |