End-to-End Imitation Learning for Optimal Asteroid Proximity Operations

TL;DR

This paper introduces an end-to-end neural network-based control system for asteroid proximity operations that improves computational efficiency and robustness in spacecraft navigation using raw sensor data.

Contribution

It presents a novel end-to-end imitation learning approach combined with a hybrid MPC controller for efficient and robust spacecraft control near asteroids.

Findings

Neural network controller achieves near-optimal control from raw sensor data.

Hybrid MPC-guided imitation learning improves computational efficiency.

Method enhances robustness in state determination and control.

Abstract

Controlling spacecraft near asteroids in deep space comes with many challenges. The delays involved necessitate heavy usage of limited onboard computation resources while fuel efficiency remains a priority to support the long loiter times needed for gathering data. Additionally, the difficulty of state determination due to the lack of traditional reference systems requires a guidance, navigation, and control (GNC) pipeline that ideally is both computationally and fuel-efficient, and that incorporates a robust state determination system. In this paper, we propose an end-to-end algorithm utilizing neural networks to generate near-optimal control commands from raw sensor data, as well as a hybrid model predictive control (MPC) guided imitation learning controller delivering improvements in computational efficiency over a traditional MPC controller.