Neural Brain: A Neuroscience-inspired Framework for Embodied Agents

TL;DR

This paper proposes a biologically inspired framework called Neural Brain for embodied AI agents, integrating sensing, perception, cognition, memory, and neuromorphic hardware to enable human-like adaptability in real-world environments.

Contribution

It introduces a unified, neuroscience-inspired architecture for Neural Brain, addressing core components and bridging the gap between static AI models and dynamic real-world adaptability.

Findings

Proposes a biologically inspired neural architecture for embodied agents

Reviews latest research and identifies gaps in current AI systems

Outlines a roadmap for developing human-level autonomous agents

Abstract

The rapid evolution of artificial intelligence (AI) has shifted from static, data-driven models to dynamic systems capable of perceiving and interacting with real-world environments. Despite advancements in pattern recognition and symbolic reasoning, current AI systems, such as large language models, remain disembodied, unable to physically engage with the world. This limitation has driven the rise of embodied AI, where autonomous agents, such as humanoid robots, must navigate and manipulate unstructured environments with human-like adaptability. At the core of this challenge lies the concept of Neural Brain, a central intelligence system designed to drive embodied agents with human-like adaptability. A Neural Brain must seamlessly integrate multimodal sensing and perception with cognitive capabilities. Achieving this also requires an adaptive memory system and energy-efficient hardware-software co-design, enabling real-time action in dynamic environments. This paper introduces a unified framework for the Neural Brain of embodied agents, addressing two fundamental challenges: (1) defining the core components of Neural Brain and (2) bridging the gap between static AI models and the dynamic adaptability required for real-world deployment. To this end, we propose a biologically inspired architecture that integrates multimodal active sensing, perception-cognition-action function, neuroplasticity-based memory storage and updating, and neuromorphic hardware/software optimization. Furthermore, we also review the latest research on embodied agents across these four aspects and analyze the gap between current AI systems and human intelligence. By synthesizing insights from neuroscience, we outline a roadmap towards the development of generalizable, autonomous agents capable of human-level intelligence in real-world scenarios.