Powered Landing Control of Reusable Rockets Based on Softmax Double DDPG
Open Access
Abstract
Multi-stage launch vehicles are currently the primary tool for humans to reach extraterrestrial space. The technology of recovering and reusing rockets can effectively shorten rocket launch cycles and reduce space launch costs. With the development of deep representation learning, reinforcement learning (RL) has become a robust learning framework capable of learning complex policies in high-dimensional environments. In this paper, a deep reinforcement learning-based reusable rocket landing control method is proposed. The mathematical process of reusable rocket landing is modelled by considering the aerodynamic drag, thrust, gravitational force, and Earth’s rotation during the landing process. A reward function is designed according to the rewards and penalties derived from mission accomplishment, terminal constraints, and landing performance. Based on this, the Softmax double deep deterministic policy gradient (SD3) deep RL method is applied to build a robust reusable rocket landing control method. In the constructed simulation environment, the proposed method can achieve convergent and robust control results, proving the effectiveness of the proposed method.Keywords
Funding Information
- Guangdong Basic and Applied Basic Research Foundation (2022A1515110837)
This publication has 23 references indexed in Scilit:
- An Overview of Reusable Launch Vehicle Technology DemonstratorCurrent Science, 2018
- Mastering the game of Go without human knowledgeNature, 2017
- Onboard Trajectory Generation for Entry Vehicles via Adaptive Multivariate Pseudospectral InterpolationJournal of Guidance, Control, and Dynamics, 2017
- Lossless Convexification of Nonconvex Control Bound and Pointing Constraints of the Soft Landing Optimal Control ProblemIEEE Transactions on Control Systems Technology, 2013
- CVXGEN: a code generator for embedded convex optimizationOptimization and Engineering, 2011
- Minimum-Landing-Error Powered-Descent Guidance for Mars Landing Using Convex OptimizationJournal of Guidance, Control, and Dynamics, 2010
- Ares I First Stage Booster Deceleration System - An Overview2009
- Ares I-X Flight Test: The Future Begins Here2008
- A status report on the development of the Kistler Aerospace K-1 Reusable Launch Vehicle2001
- Design and testing of the K-1 Reusable Launch Vehicle landing system airbags1999