arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1901.04473eess.SYcs.ROcs.SY
收藏

基于强化元学习的自适应制导

Adaptive Guidance with Reinforcement Meta-Learning

DeepAnalytX LLC(DeepAnalytX有限责任公司);Massachusetts Institute of Technology(麻省理工学院)

Brian Gaudet, Richard Linares

AI总结:

本文提出一种基于强化元学习和循环策略的自适应制导系统,能实时适应环境力,在火星着陆等复杂任务中表现优异,并实现了制导与导航的集成。

摘要:

本文提出了一种使用强化元学习结合循环策略和价值函数近似器开发的全新自适应制导系统。循环网络层的使用使得部署的策略能够实时适应作用于智能体上的环境力。我们在四个具有未知但高度可变动力学的困难任务中,比较了DR/DV制导律、使用非循环策略的RL智能体以及使用循环策略的RL智能体的性能。这些任务包括发生随机引擎故障的安全火星着陆,以及在未知环境动力学下的小行星着陆。我们还展示了循环策略仅利用多普勒雷达高度计回波进行导航的能力,从而实现了制导与导航的集成。

英文摘要:

This paper proposes a novel adaptive guidance system developed using reinforcement meta-learning with a recurrent policy and value function approximator. The use of recurrent network layers allows the deployed policy to adapt real time to environmental forces acting on the agent. We compare the performance of the DR/DV guidance law, an RL agent with a non-recurrent policy, and an RL agent with a recurrent policy in four difficult tasks with unknown but highly variable dynamics. These tasks include a safe Mars landing with random engine failure and a landing on an asteroid with unknown environmental dynamics. We also demonstrate the ability of a recurrent policy to navigate using only Doppler radar altimeter returns, thus integrating guidance and navigation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑