The Safe Trusted Autonomy for Responsible Space Program

TL;DR

This paper discusses the STARS program's progress in developing trustworthy autonomous satellite systems using reinforcement learning, runtime assurance, and human-autonomy interfaces, highlighting integration and initial analysis results.

Contribution

It introduces an integrated testing environment for collaborative autonomous satellites and reports on the implementation of reinforcement learning and assurance algorithms within this framework.

Findings

Analysis of reinforcement learning multi-satellite control algorithms

Implementation of runtime assurance approaches

Development of a human-autonomy teaming interface

Abstract

The Safe Trusted Autonomy for Responsible Space (STARS) program aims to advance autonomy technologies for space by leveraging machine learning technologies while mitigating barriers to trust, such as uncertainty, opaqueness, brittleness, and inflexibility. This paper presents the achievements and lessons learned from the STARS program in integrating reinforcement learning-based multi-satellite control, run time assurance approaches, and flexible human-autonomy teaming interfaces, into a new integrated testing environment for collaborative autonomous satellite systems. The primary results describe analysis of the reinforcement learning multi-satellite control and run time assurance algorithms. These algorithms are integrated into a prototype human-autonomy interface using best practices from human-autonomy trust literature, however detailed analysis of the effectiveness is left to future work. References are provided with additional detailed results of individual experiments.