Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation

2025-09-17

AI Summary

Spacecraft pose estimation (SPE) suffers significant performance degradation on real-world imagery due to distributional shift between synthetic training data and real test domains; existing unsupervised domain adaptation (UDA) methods yield limited gains under scarce target-domain annotations. This paper pioneers the application of *supervised* domain adaptation to 6-DoF SPE, proposing a lightweight Learning Invariant Representations and Risks (LIRR) framework. LIRR jointly optimizes for domain-invariant features and task-specific risk minimization, requiring only minimal real-world annotations (e.g., 5% of target labels). On the SPEED+ benchmark, it surpasses fully supervised baselines while imposing no architectural constraints—remaining compatible with arbitrary backbone networks. It consistently outperforms source-only training, fine-tuning, and state-of-the-art UDA and semi-supervised DA baselines. The method offers an efficient, robust, and hardware-deployable solution for onboard real-time spacecraft pose estimation.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Mobility, Driving & Flight

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Spacecraft Pose Estimation (SPE) is a fundamental capability for autonomous space operations such as rendezvous, docking, and in-orbit servicing. Hybrid pipelines that combine object detection, keypoint regression, and Perspective-n-Point (PnP) solvers have recently achieved strong results on synthetic datasets, yet their performance deteriorates sharply on real or lab-generated imagery due to the persistent synthetic-to-real domain gap. Existing unsupervised domain adaptation approaches aim to mitigate this issue but often underperform when a modest number of labeled target samples are available. In this work, we propose the first Supervised Domain Adaptation (SDA) framework tailored for SPE keypoint regression. Building on the Learning Invariant Representation and Risk (LIRR) paradigm, our method jointly optimizes domain-invariant representations and task-specific risk using both labeled synthetic and limited labeled real data, thereby reducing generalization error under domain shift. Extensive experiments on the SPEED+ benchmark demonstrate that our approach consistently outperforms source-only, fine-tuning, and oracle baselines. Notably, with only 5% labeled target data, our method matches or surpasses oracle performance trained on larger fractions of labeled data. The framework is lightweight, backbone-agnostic, and computationally efficient, offering a practical pathway toward robust and deployable spacecraft pose estimation in real-world space environments.

Problem

• Bridging synthetic-real domain gap in spacecraft pose estimation
• Improving performance on real imagery with limited labeled data
• Developing supervised domain adaptation for keypoint regression

Innovation

• Supervised Domain Adaptation for spacecraft pose
• Joint optimization of invariant representations and risk
• Lightweight backbone-agnostic framework with limited real data