COFFEE: A Shadow-Resilient Real-Time Pose Estimator for Unknown Tumbling Asteroids using Sparse Neural Networks

2025-08-05

AI Summary

Real-time pose estimation of tumbling asteroids under severe self-occlusion and cast shadows remains challenging; conventional feature-based methods lack robustness, while deep learning approaches suffer from high computational overhead and sensitivity to shadow interference. Method: We propose a shadow-aware sparse feature selection mechanism integrated with solar phase angle priors, enabling joint modeling of object contours and projected shadows. A collaborative training architecture combines a sparse neural network with an attention-based graph neural network to achieve dynamic shadow-invariant feature detection and inter-frame matching. Contribution/Results: Our method achieves, for the first time, bias-free real-time pose estimation for chaotic tumblers. Evaluated on synthetic datasets and realistic Apophis renderings, it outperforms traditional methods in accuracy and accelerates inference by an order of magnitude over state-of-the-art deep models. This significantly enhances the robustness and reliability of spacecraft state estimation in deep-space missions.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The accurate state estimation of unknown bodies in space is a critical challenge with applications ranging from the tracking of space debris to the shape estimation of small bodies. A necessary enabler to this capability is to find and track features on a continuous stream of images. Existing methods, such as SIFT, ORB and AKAZE, achieve real-time but inaccurate pose estimates, whereas modern deep learning methods yield higher quality features at the cost of more demanding computational resources which might not be available on space-qualified hardware. Additionally, both classical and data-driven methods are not robust to the highly opaque self-cast shadows on the object of interest. We show that, as the target body rotates, these shadows may lead to large biases in the resulting pose estimates. For these objects, a bias in the real-time pose estimation algorithm may mislead the spacecraft's state estimator and cause a mission failure, especially if the body undergoes a chaotic tumbling motion. We present COFFEE, the Celestial Occlusion Fast FEature Extractor, a real-time pose estimation framework for asteroids designed to leverage prior information on the sun phase angle given by sun-tracking sensors commonly available onboard spacecraft. By associating salient contours to their projected shadows, a sparse set of features are detected, invariant to the motion of the shadows. A Sparse Neural Network followed by an attention-based Graph Neural Network feature matching model are then jointly trained to provide a set of correspondences between successive frames. The resulting pose estimation pipeline is found to be bias-free, more accurate than classical pose estimation pipelines and an order of magnitude faster than other state-of-the-art deep learning pipelines on synthetic data as well as on renderings of the tumbling asteroid Apophis.

Problem

• Real-time pose estimation for unknown tumbling asteroids
• Robust feature extraction despite opaque self-cast shadows
• Balancing accuracy and computational efficiency on space hardware

Innovation

• Sparse Neural Networks for feature extraction
• Attention-based Graph Neural Network for matching
• Shadow-resilient real-time pose estimation