From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

TL;DR

This paper introduces BSC-Nav, a brain-inspired framework that constructs structured spatial memory for embodied agents, significantly improving navigation capabilities and generalization in complex real-world environments.

Contribution

It presents a unified, biologically inspired approach to build and utilize structured spatial memory in embodied agents, enhancing navigation and adaptability.

Findings

Achieves state-of-the-art performance in navigation tasks

Demonstrates strong zero-shot generalization

Supports versatile embodied behaviors in real-world settings

Abstract

Spatial cognition enables adaptive goal-directed behavior by constructing internal models of space. Robust biological systems consolidate spatial knowledge into three interconnected forms: \textit{landmarks} for salient cues, \textit{route knowledge} for movement trajectories, and \textit{survey knowledge} for map-like representations. While recent advances in multi-modal large language models (MLLMs) have enabled visual-language reasoning in embodied agents, these efforts lack structured spatial memory and instead operate reactively, limiting their generalization and adaptability in complex real-world environments. Here we present Brain-inspired Spatial Cognition for Navigation (BSC-Nav), a unified framework for constructing and leveraging structured spatial memory in embodied agents. BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals. Integrated with powerful MLLMs, BSC-Nav achieves state-of-the-art efficacy and efficiency across diverse navigation tasks, demonstrates strong zero-shot generalization, and supports versatile embodied behaviors in the real physical world, offering a scalable and biologically grounded path toward general-purpose spatial intelligence.