RoboMemory：一種受大腦啟發的多記憶代理框架，用於物理具身系統中的終身學習

RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 2, 2025

作者: Mingcong Lei, Honghao Cai, Zezhou Cui, Liangchen Tan, Junkun Hong, Gehan Hu, Shuangyu Zhu, Yimou Wu, Shaohan Jiang, Ge Wang, Zhen Li, Shuguang Cui, Yiming Zhao, Yatong Han

cs.AI

摘要

我們提出RoboMemory，這是一個受大腦啟發的多記憶框架，專為物理具身系統的終身學習而設計，旨在解決現實環境中的關鍵挑戰：持續學習、多模組記憶延遲、任務關聯捕捉以及閉環規劃中的無限迴圈緩解。基於認知神經科學，它整合了四個核心模組：資訊預處理器（類似丘腦）、終身具身記憶系統（類似海馬體）、閉環規劃模組（類似前額葉）以及低階執行器（類似小腦），以實現長期規劃和累積學習。作為框架的核心，終身具身記憶系統通過在空間、時間、情景和語義子模組之間進行並行更新/檢索，緩解了複雜記憶框架中的推理速度問題。它結合了動態知識圖譜（KG）和一致的架構設計，以增強記憶的一致性和可擴展性。在EmbodiedBench上的評估顯示，RoboMemory在平均成功率上比開源基準（Qwen2.5-VL-72B-Ins）高出25%，並超越閉源最先進技術（SOTA）（Claude3.5-Sonnet）5%，建立了新的SOTA。消融研究驗證了關鍵組件（批評者、空間記憶、長期記憶），而實際部署則證實了其終身學習能力，在重複任務中的成功率顯著提高。RoboMemory通過可擴展性緩解了高延遲挑戰，為在物理機器人中整合多模態記憶系統提供了基礎參考。

English

We present RoboMemory, a brain-inspired multi-memory framework for lifelong learning in physical embodied systems, addressing critical challenges in real-world environments: continuous learning, multi-module memory latency, task correlation capture, and infinite-loop mitigation in closed-loop planning. Grounded in cognitive neuroscience, it integrates four core modules: the Information Preprocessor (thalamus-like), the Lifelong Embodied Memory System (hippocampus-like), the Closed-Loop Planning Module (prefrontal lobe-like), and the Low-Level Executer (cerebellum-like) to enable long-term planning and cumulative learning. The Lifelong Embodied Memory System, central to the framework, alleviates inference speed issues in complex memory frameworks via parallelized updates/retrieval across Spatial, Temporal, Episodic, and Semantic submodules. It incorporates a dynamic Knowledge Graph (KG) and consistent architectural design to enhance memory consistency and scalability. Evaluations on EmbodiedBench show RoboMemory outperforms the open-source baseline (Qwen2.5-VL-72B-Ins) by 25% in average success rate and surpasses the closed-source State-of-the-Art (SOTA) (Claude3.5-Sonnet) by 5%, establishing new SOTA. Ablation studies validate key components (critic, spatial memory, long-term memory), while real-world deployment confirms its lifelong learning capability with significantly improved success rates across repeated tasks. RoboMemory alleviates high latency challenges with scalability, serving as a foundational reference for integrating multi-modal memory systems in physical robots.