空间控制技术与应用2025，Vol.51Issue(4)：65-77,13.DOI:10.3969/j.issn.1674-1579.2025.04.006
空间自主感知语义分割模型的可解释性研究
Interpretability Research on Semantic Segmentation Models in Spatial Autonomous Perception
摘要
Abstract
With the continuous advancement of deep space exploration and intelligent autonomous systems,semantic segmentation models have demonstrated growing value in spatial environmental perception,playing a critical role in planetary terrain recognition,path planning,and risk assessment tasks for space-based autonomous sensing.However,most deep learning-based semantic segmentation models adopt a"black-box"architecture,making their internal decision-making processes difficult to interpret.This lack of interpretability significantly limits their credibility and controllability in mission-critical scenarios.To address the current deficiency of interpretability research in semantic segmentation models for space-based autonomous perception,this study investigates a perturbation-based interpretability approach—RISE(Randomized Input Sampling for Explanation)—in combination with a deletion mechanism,using representative Mars remote sensing imagery.By visualizing and intervening in the pixel-level saliency regions of the model,and systematically analyzing variations in heatmaps under different saliency mask settings along with the corresponding effects of region deletion on model predictions,this work reveals the model's reliance on specific features for terrain classification.Findings indicate issues such as excessive dependence on color and overlapping saliency regions across categories.On this basis,the study proposes targeted optimization strategies to enhance model transparency and reliability,providing theoretical support and technical pathways for the interpretable deployment of semantic segmentation models in space-based autonomous systems.关键词
空间自主感知/语义分割模型/星表地形/可解释性/RISE方法/模型优化Key words
spatial autonomous perception/semantic segmentation model/planetary surface terrain/interpretability/RISE method/model optimization分类
航空航天引用本文复制引用
郝仁剑,胡勇,施沐伽,屈金硕,冯李航,王东..空间自主感知语义分割模型的可解释性研究[J].空间控制技术与应用,2025,51(4):65-77,13.基金项目
国家自然科学基金资助项目(U21B6001)和北京市高层次创新创业人才支持计划科技新星计划资助项目(20220484027) National Natural Science Foundation of China(61333008)and Beijing Nova Program(20220484027) （U21B6001）
