DVD-MapAL: Deep Visual Feature-Driven Map-Assisted Localization for Planetary Spacecraft Exploration

Spacecraft autonomous localization is a fundamental capability for space missions, including rover planetary surface exploration, satellite on-orbit servicing and lander precision landing tasks. While conventional approaches predominantly depend on ground-based observatories, their lack of autonomy and scalability limits their applications in deep-space exploration tasks. This paper presents Deep Visual Feature-Driven Map-Assisted Localization (DVD-MapAL), a novel method that combines visual odometry with prior map constraints to establish a self-contained localization system. The proposed architecture introduces two key innovations: (1) a coordinate-constrained pose optimization module that dynamically corrects cumulative errors in visual odometry through geometric consistency verification, and (2) a lightweight deep feature descriptor with a spatial inhibition mechanism enabling robust projection estimation between orbital imagery and pre-existing maps. We release a comprehensive simulation dataset containing 11,721 photorealistic images with six-degree-of-freedom annotations, generated through Unreal Engine and AirSim platforms. Experimental evaluations demonstrate DVD-MapAL’s superior performance, achieving 23.64% lower mean positional error than ORB-SLAM3 in spacecraft scenarios. Further validation on real-world datasets reveals 17.89% improvement over conventional visual localization methods, particularly in feature-deprived extraterrestrial environments. The open-source implementation and benchmark dataset will be made publicly available.