☆ 4.6 Article Proceedings Paper

Robust interplanetary trajectory design under multiple uncertainties via meta-reinforcement learning

ACTA ASTRONAUTICA (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Aerospace

Physics-Informed Neural Networks for Optimal Planar Orbit Transfers

Enrico Schiassi et al.

Summary: This paper presents a novel framework that combines the indirect method and Physics-Informed Neural Networks (PINNs) to learn optimal control actions for a series of optimal planar orbit transfer problems. The framework utilizes the indirect method to retrieve the optimal control by applying the Pontryagin minimum principle, and PINNs are used to model a neural network representation of the state-costate pair while satisfying the physics constraints of the problem.

JOURNAL OF SPACECRAFT AND ROCKETS (2022)

添加到收藏夹

Article Engineering, Aerospace

Image-Based Deep Reinforcement Meta-Learning for Autonomous Lunar Landing

Andrea Scorsoglio et al.

Summary: In this paper, image-based reinforcement metalearning is used to solve the lunar pinpoint powered descent and landing task. The algorithm demonstrates autonomous guidance and navigation capabilities, reaching meter-level accuracy even with partial observations and unknown spacecraft states.

JOURNAL OF SPACECRAFT AND ROCKETS (2022)

添加到收藏夹

Article Engineering, Aerospace

Image-Based Meta-Reinforcement Learning for Autonomous Guidance of an Asteroid Impactor

Lorenzo Federici et al.

Summary: This paper investigates the use of meta-reinforcement learning for autonomous guidance of a spacecraft in the terminal phase of impacting a binary asteroid system. It proposes replacing the control policy with a convolutional-recurrent neural network that maps optical observations to control thrust and thrusting times. The network is trained using a reinforcement learning method called proximal policy optimization algorithm. The study demonstrates that the guidance system can successfully steer the spacecraft to the final impact point in over 98% of the tested scenarios.

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS (2022)

添加到收藏夹

Article Engineering, Aerospace

Convex Approach to Covariance Control with Application to Stochastic Low-Thrust Trajectory Optimization

Boris Benedikter et al.

Summary: This paper outlines a novel approach for designing optimal space trajectories under significant uncertainty. It employs finite-horizon covariance control and a robust feedback controller to plan an optimal path and compensate for disturbances during flight. A mindful convexification strategy is used to convert the nonlinear control problem into a convex optimization problem. The relaxation of the problem is proven to be lossless through optimal control theory and numerical experiments.

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS (2022)

添加到收藏夹

Article Engineering, Aerospace

Meta-reinforcement learning for adaptive spacecraft guidance during finite-thrust rendezvous missions

Lorenzo Federici et al.

Summary: This paper investigates a meta-reinforcement learning approach to design an adaptive guidance algorithm for multiple rendezvous missions. The study shows that the recurrent-network-based meta-reinforcement learning approach is able to better meet the task requirements.

ACTA ASTRONAUTICA (2022)

添加到收藏夹

Article Engineering, Aerospace

Autonomous closed-loop guidance using reinforcement learning in a low-thrust, multi-body dynamical environment

Nicholas B. LaFarge et al.

Summary: The study utilizes reinforcement learning to create a 'lightweight' closed-loop controller for guiding low-thrust spacecraft in challenging dynamic environments. The controller functions without direct knowledge of the dynamical model and is trained using high-performance computing to generate real-time control profiles.

ACTA ASTRONAUTICA (2021)

添加到收藏夹

Article Engineering, Aerospace

Deep Learning Techniques for Autonomous Spacecraft Guidance During Proximity Operations

Lorenzo Federici et al.

Summary: This study investigates the use of deep learning techniques for real-time optimal spacecraft guidance during terminal rendezvous maneuvers, comparing the performance of behavioral cloning and reinforcement learning on a linear multi-impulsive rendezvous mission.

JOURNAL OF SPACECRAFT AND ROCKETS (2021)

添加到收藏夹

Article Engineering, Aerospace

Reinforcement Learning for Robust Trajectory Design of Interplanetary Missions

Alessandro Zavoli et al.

Summary: This paper examines the use of reinforcement learning to design low-thrust interplanetary trajectories in the presence of uncertainties and disturbances, and utilizes the Proximal Policy Optimization algorithm to train a deep neural network for optimal control policy mapping. The resulting guidance and control network produces robust trajectories and closed-loop guidance laws. Numerical results and Monte Carlo campaigns validate the proposed approach.

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS (2021)

添加到收藏夹

Article Engineering, Aerospace

Minimum-Fuel Closed-Loop Powered Descent Guidance with Stochastically Derived Throttle Margins

Jack Ridderhof et al.

Summary: In this paper, a method is proposed to adjust bounds on feed-forward optimal thrust magnitude command by modeling the powered descent trajectory as a stochastic process, allowing for sufficient feedback authority. This approach aims to prevent overly conservative margins and ensure closed-loop throttle is within allowable limits with high probability. The method is designed to be solved onboard without the need for iteration.

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS (2021)

添加到收藏夹

Article Engineering, Aerospace

Direct multiple shooting transcription with polynomial algebra for optimal control problems under uncertainty

Cristian Greco et al.

ACTA ASTRONAUTICA (2020)

添加到收藏夹

Article Engineering, Aerospace

Deep reinforcement learning for six degree-of-freedom planetary landing

Brian Gaudet et al.

ADVANCES IN SPACE RESEARCH (2020)

添加到收藏夹

Article Engineering, Aerospace

Six degree-of-freedom body-fixed hovering over unmapped asteroids via LIDAR altimetry and reinforcement meta-learning

Brian Gaudet et al.

ACTA ASTRONAUTICA (2020)

添加到收藏夹

Article Engineering, Aerospace

Terminal adaptive guidance via reinforcement meta-learning: Applications to autonomous asteroid close-proximity operations

Brian Gaudet et al.

ACTA ASTRONAUTICA (2020)

添加到收藏夹

Article Engineering, Aerospace

Tube Stochastic Optimal Control for Nonlinear Constrained Trajectory Optimization Problems

Naoya Ozaki et al.

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS (2020)

添加到收藏夹

Review Robotics

Deep learning in robotics: a review of recent research

Harry A. Pierson et al.

ADVANCED ROBOTICS (2017)

添加到收藏夹

Article Engineering, Aerospace

Automated Missed-Thrust Propellant Margin Analysis for Low-Thrust Trajectories

Frank E. Laipert et al.

JOURNAL OF SPACECRAFT AND ROCKETS (2015)

添加到收藏夹

Article Engineering, Aerospace

Tour of Jupiter Galilean moons: Winning solution of GTOC6

Guido Colasurdo et al.

ACTA ASTRONAUTICA (2014)

添加到收藏夹

Article Operations Research & Management Science

A Hybrid Differential Dynamic Programming Algorithm for Constrained Optimal Control Problems. Part 2: Application

Gregory Lantoine et al.

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS (2012)

添加到收藏夹

Article Engineering, Aerospace

Coupling of system resource margins through the use of electric propulsion: Implications in preparing for the Dawn mission to Ceres and Vesta

Marc D. Rayman et al.

ACTA ASTRONAUTICA (2007)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Meta-learning in Reinforcement Learning

N Schweighofer et al.

NEURAL NETWORKS (2003)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.