# Adaptive Guidance and Integrated Navigation with Reinforcement Meta-Learning

## TL;DR

This paper introduces an adaptive guidance system using reinforcement meta-learning with recurrent networks, enabling real-time adaptation to environmental forces for complex landing tasks on Mars and asteroids.

## Contribution

It presents a novel reinforcement meta-learning approach with recurrent policies for adaptive guidance and integrated navigation in challenging, dynamic environments.

## Key findings

- Recurrent policies outperform non-recurrent RL in variable environments.
- Meta-learning enables real-time adaptation to environmental forces.
- Guidance laws can be implemented using only Doppler and LIDAR altimeter readings.

## Abstract

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 challenging environments 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 RL meta-learning optimized policy to implement a guidance law using observations consisting of only Doppler radar altimeter readings in a Mars landing environment, and LIDAR altimeter readings in an asteroid landing environment, thus integrating guidance and navigation.