Autonomous navigation in unknown environments requires compact yet expressive spatial understanding under partial observability to support high-level decision making. Existing approaches struggle to balance rich contextual representation with navigation efficiency. We present MacroNav, a learning-based navigation framework featuring two key components: (1) a lightweight context encoder trained via multi-task self-supervised learning to capture multi-scale, navigation-centric spatial representations; and (2) a reinforcement learning policy that seamlessly integrates these representations with graph-based reasoning for efficient action selection. Extensive experiments demonstrate the context encoder's efficient and robust environmental understanding. Real-world deployments further validate MacroNav's effectiveness, yielding significant gains over state-of-the-art navigation methods in both Success Rate (SR) and Success weighted by Path Length (SPL), while maintaining low computational cost. Code will be released upon acceptance.

翻译：未知环境中的自主导航需要在部分可观测条件下，以紧凑且富有表现力的空间理解来支持高层决策。现有方法难以在丰富的上下文表示与导航效率之间取得平衡。我们提出了MacroNav，一种基于学习的导航框架，包含两个关键组件：(1) 通过多任务自监督学习训练的轻量级上下文编码器，用于捕获多尺度、以导航为中心的空间表示；(2) 一种强化学习策略，将这些表示与基于图的推理无缝集成，以实现高效的动作选择。大量实验证明了上下文编码器对环境的高效且鲁棒的理解能力。实际部署进一步验证了MacroNav的有效性，在成功率(SR)和路径长度加权成功率(SPL)方面均显著优于现有最先进的导航方法，同时保持了较低的计算成本。代码将在论文被接受后发布。