A Photorealistic Dataset and Vision-Based Algorithm for Anomaly Detection During Proximity Operations in Lunar Orbit

TL;DR

This paper introduces a new benchmark dataset and a novel model-based anomaly detection algorithm for space environments, specifically targeting hazard detection for lunar orbit operations with high accuracy.

Contribution

The paper presents ALLO, a synthetic dataset for space anomaly detection, and MRAD, a model-based algorithm that outperforms existing methods in lunar orbit scenarios.

Findings

MRAD achieves 62.9% AP at pixel level

MRAD attains 75.0% AUROC at image level

State-of-the-art methods often fail in space domain

Abstract

NASA's forthcoming Lunar Gateway space station, which will be uncrewed most of the time, will need to operate with an unprecedented level of autonomy. One key challenge is enabling the Canadarm3, the Gateway's external robotic system, to detect hazards in its environment using its onboard inspection cameras. This task is complicated by the extreme and variable lighting conditions in space. In this paper, we introduce the visual anomaly detection and localization task for the space domain and establish a benchmark based on a synthetic dataset called ALLO (Anomaly Localization in Lunar Orbit). We show that state-of-the-art visual anomaly detection methods often fail in the space domain, motivating the need for new approaches. To address this, we propose MRAD (Model Reference Anomaly Detection), a statistical algorithm that leverages the known pose of the Canadarm3 and a CAD model of the Gateway to generate reference images of the expected scene appearance. Anomalies are then identified as deviations from this model-generated reference. On the ALLO dataset, MRAD surpasses state-of-the-art anomaly detection algorithms, achieving an AP score of 62.9% at the pixel level and an AUROC score of 75.0% at the image level. Given the low tolerance for risk in space operations and the lack of domain-specific data, we emphasize the need for novel, robust, and accurate anomaly detection methods to handle the challenging visual conditions found in lunar orbit and beyond.