Paper published in IEEE Transactions on Aerospace and Electronic Systems

Please see the following text and figure for the TAES paper website post: "Our latest article, "Surrogate-aided Learning of Active Tether-Net Maneuver to Capture Rotating Space Debris," has been published in the journal IEEE Transactions on Aerospace and Electronic Systems!

In the article, co-written with Dr. Souma Chowdhury's ADAMS lab, we present neural network-based policies to guide the thrust actions of a robotic tether-net system used for space debris capture, trained using reinforcement learning (RL). Each debris capture operation is modeled as a Markov Decision Process with the state encompassing the target's pose relative to the chaser, and solved using a policy gradient approach. A special reward function is formulated to account for both the primary objectives of capture success metrics and fuel consumptions incurred, and intermediate objectives related to hypothesized favorable intermediate states of the net that facilitate good capture performance and alleviate reward sparsity during RL training. Significant improvement in capture performance, from around 5.7% (with random actions) to 85% is achieved via training. Tested over unseen scenarios, the best RL-derived policy readily outperforms an aiming-point-based baseline, with the nature of actions providing important insights into net behavior (e.g., active net rotation and maximal mouth opening) favorable to capture success and low fuel consumption by the system.

The paper can be read via the following link: https://ieeexplore.ieee.org/document/11214442

Supplementary video results for the paper are also available via the following link: https://github.com/adamslab-ub/Learning-Tether-Net-Maneuver-IEEE-TAES-2025