Learning Robust Policies for Generalized Debris Capture with an Automated Tether-Net System

TL;DR

This paper develops a reinforcement learning-based control policy for a tether-net system to reliably capture space debris, effectively handling uncertainties and varying scenarios with near-optimal performance.

Contribution

It introduces a PPO2 reinforcement learning framework integrated with net dynamics simulations for generalized debris capture control.

Findings

The learned policy achieves high capture success across diverse scenarios.

The approach handles uncertainties in sensing and actuation effectively.

Performance is comparable to scenario-specific optimization methods.

Abstract

Tether-net launched from a chaser spacecraft provides a promising method to capture and dispose of large space debris in orbit. This tether-net system is subject to several sources of uncertainty in sensing and actuation that affect the performance of its net launch and closing control. Earlier reliability-based optimization approaches to design control actions however remain challenging and computationally prohibitive to generalize over varying launch scenarios and target (debris) state relative to the chaser. To search for a general and reliable control policy, this paper presents a reinforcement learning framework that integrates a proximal policy optimization (PPO2) approach with net dynamics simulations. The latter allows evaluating the episodes of net-based target capture, and estimate the capture quality index that serves as the reward feedback to PPO2. Here, the learned policy is designed to model the timing of the net closing action based on the state of the moving net and the target, under any given launch scenario. A stochastic state transition model is considered in order to incorporate synthetic uncertainties in state estimation and launch actuation. Along with notable reward improvement during training, the trained policy demonstrates capture performance (over a wide range of launch/target scenarios) that is close to that obtained with reliability-based optimization run over an individual scenario.