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

TL;DR

RoboMemory is a brain-inspired framework that integrates multiple memory types to enhance long-term, interactive learning and reasoning in embodied robots, demonstrating significant performance improvements in real-world tasks.

Contribution

The paper introduces RoboMemory, a novel multi-memory agentic framework that unifies various memory systems with a dynamic knowledge graph and adaptive planner for improved robotic learning.

Findings

Improves success rate by 26.5% over baseline

Outperforms state-of-the-art models like Claude-3.5-Sonnet

Demonstrates effective cumulative learning in real-world trials

Abstract

Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and inefficient integration of heterogeneous memories, limiting their capacity for long-horizon adaptation. To address this, we introduce RoboMemory, a brain-inspired framework that unifies Spatial, Temporal, Episodic, and Semantic memory within a parallelized architecture for efficient long-horizon planning and interactive learning. Its core innovations are a dynamic spatial knowledge graph for scalable, consistent memory updates and a closed-loop planner with a critic module for adaptive decision-making. Extensive experiments on EmbodiedBench show that RoboMemory, instantiated with Qwen2.5-VL-72B-Ins, improves the average success rate by 26.5% over its strong baseline and even surpasses the closed-source SOTA, Claude-3.5-Sonnet. Real-world trials further confirm its capability for cumulative learning, with performance consistently improving over repeated tasks. Our results position RoboMemory as a scalable foundation for memory-augmented embodied agents, bridging insights from cognitive neuroscience with practical robotic autonomy.