面向具身智能的记忆原生非地面网络
Memory-Native Non-Terrestrial Networks for Embodied Intelligence
浏览论文内容
中文总结 AI 辅助
针对非地面网络与具身智能协同中的动态资源受限问题，提出记忆原生NTN范式，通过双记忆架构（物理记忆与数字记忆）实现跨层记忆增强决策，在卫星具身问答任务中显著优于传统方法。
中文摘要 AI 辅助
非地面网络（NTN）为具身智能（EI）提供无处不在的连接，使野外机器人能够利用云资源或向远程中心报告关键信息。然而，由于高度动态、资源受限、拓扑变化和任务导向的环境，这种协同并非易事。现有的无记忆NTN协议效率低下，因为决策由局部信道条件和瞬时服务需求驱动。为了解决这些局限性，本文提出了记忆原生NTN（MemNTN）范式，利用长程上下文进行记忆增强的系统优化。为了实现这一范式转变，我们建立了一个双记忆架构，区分了表示世界状态的物理记忆和编码历史网络经验的数字记忆。我们开发了记忆获取、压缩、估值、更新和利用机制，促进了从物理层和接入层到网络层和应用层的跨层、记忆原生决策。在卫星具身问答（SEQA）实验中的结果表明，所提出的MemNTN显著优于传统的无状态NTN和地面方法。
英文摘要
Non-terrestrial networks (NTN) provide ubiquitous connectivity for embodied intelligence (EI), enabling robots in the wilderness to leverage cloud resources or report critical information to remote centers. However, the synergy is nontrivial due to the highly dynamic, resource-constrained, topology-varying, and task-oriented environment. Existing memoryless NTN protocols become inefficient, since the decisions are driven by local channel conditions and instantaneous service demands. To address these limitations, this paper proposes the memory-native NTN (Mem-NTN) paradigm that leverages long-horizon contexts for memory-augmented system optimization. To realize this paradigm shift, we establish a dual-memory architecture that distinguishes between physical memory representing the state of the world and digital memory encoding historical network experience. We develop memory acquisition, compression, valuation, update, and utilization mechanisms that facilitate cross-layer, memory-native decision-making, spanning from the physical and access layers up to the network and application layers. Experiments in satellite embodied question answering (SEQA) demonstrate that the proposed Mem-NTN consistently outperforms conventional stateless NTN and terrestrial approaches.
发表机构
- The University of Hong Kong（香港大学）
- Southern University of Science and Technology（南方科技大学）
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
- University of Macau（澳门大学）
- Istanbul Medipol University（伊斯坦布尔梅迪波尔大学）
机构由 AI 辅助整理，请以论文原文为准。
