Demonstrating Reinforcement Learning and Run Time Assurance for Spacecraft Inspection Using Unmanned Aerial Vehicles

TL;DR

This paper demonstrates the use of reinforcement learning-trained neural network controllers combined with run time assurance to ensure safe, robust autonomous spacecraft inspection using UAVs that emulate spacecraft dynamics.

Contribution

It introduces a novel approach combining neural network controllers trained with reinforcement learning and run time safety assurance for autonomous spacecraft inspection.

Findings

Neural network controllers successfully perform inspection tasks.

Run time assurance enforces safety constraints in real time.

Algorithms show robustness to real-world disturbances.

Abstract

On-orbit spacecraft inspection is an important capability for enabling servicing and manufacturing missions and extending the life of spacecraft. However, as space operations become increasingly more common and complex, autonomous control methods are needed to reduce the burden on operators to individually monitor each mission. In order for autonomous control methods to be used in space, they must exhibit safe behavior that demonstrates robustness to real world disturbances and uncertainty. In this paper, neural network controllers (NNCs) trained with reinforcement learning are used to solve an inspection task, which is a foundational capability for servicing missions. Run time assurance (RTA) is used to assure safety of the NNC in real time, enforcing several different constraints on position and velocity. The NNC and RTA are tested in the real world using unmanned aerial vehicles designed to emulate spacecraft dynamics. The results show this emulation is a useful demonstration of the capability of the NNC and RTA, and the algorithms demonstrate robustness to real world disturbances.