用双曲空间动态记忆，让机器人跨场景学习不遗忘。
HyperDCM: Dynamic Cluster Memory Replay in Hyperbolic Space for Continual Robotic Navigation Across Scenes
- 用视觉语言模型提取场景三元组，通过图网络编码成嵌入。
- 在双曲空间中投影，提升结构区分度与知识保留能力。
- 动态聚类选样本重放，适合需要长期学习的机器人导航任务。
持续学习在视觉导航中仍面临灾难性遗忘和适应多样化、动态环境的挑战。为此，我们提出双曲动态聚类记忆（HyperDCM），一种结构感知的记忆机制，通过场景图建模与合理记忆重放，增强基于扩散策略的导航性能。HyperDCM利用大视觉语言模型从RGB观测中提取语义场景三元组，通过关系图卷积网络（R-GCN）编码为场景图嵌入，并将其投影至双曲空间以提升结构可分性与持续导航中的知识保留。采用动态聚类与结构敏感更新策略，选择代表性样本进行记忆重放，有效保持知识多样性并缓解灾难性遗忘。在多个室内与室外多场景数据集上的实验表明，HyperDCM相较于适配扩散策略导航的代表性持续学习基线，在过往导航能力保留与泛化性能上均表现更优。
原文摘要 · Abstract (English)
Continual learning in visual navigation remains challenging due to catastrophic forgetting and the difficulties associated with adapting to diverse and evolving environments. To address these issues, we propose Hyperbolic Dynamic Cluster Memory (HyperDCM), a structure-aware memory mechanism that enhances diffusion policy-based navigation through scene graph modeling and principled memory replay. HyperDCM extracts semantic scene triples from RGB observations using large vision-language models, encodes them into scene graph embeddings via a Relational Graph Convolutional Network (R-GCN), and projects the embeddings into hyperbolic space to enhance structural separability and retention in continual navigation. A dynamic clustering and structure-sensitive update strategy selects representative samples for memory replay, thereby preserving knowledge diversity and mitigating catastrophic forgetting. Experiments on multi-scene indoor and outdoor datasets demonstrate that HyperDCM achieves superior retention of past navigation capabilities and improved generalization compared to representative continual learning baselines adapted to diffusion policy navigation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。