Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chan, Nga Teng, Zhang, Yi, Liu, Yechi, Cui, Renwen, Zeng, Fanhu, Ding, Zeyuan, Ren, Xiancong, Zhang, Zhang, Chen, Qifeng, Liu, Jian, Dai, Yong, Ju, Xiaozhu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917508463722496
author Chan, Nga Teng
Zhang, Yi
Liu, Yechi
Cui, Renwen
Zeng, Fanhu
Ding, Zeyuan
Ren, Xiancong
Zhang, Zhang
Chen, Qifeng
Liu, Jian
Dai, Yong
Ju, Xiaozhu
author_facet Chan, Nga Teng
Zhang, Yi
Liu, Yechi
Cui, Renwen
Zeng, Fanhu
Ding, Zeyuan
Ren, Xiancong
Zhang, Zhang
Chen, Qifeng
Liu, Jian
Dai, Yong
Ju, Xiaozhu
contents The ability to navigate and interact with complex environments is central to real-world embodied agents, yet navigation in unseen environments remains challenging due to "experiential amnesia," where existing trajectory-driven or reactive policies fail to synthesize generalizable strategies from past interactions. We propose Robo-Cortex, a self-evolving framework that enables robots to autonomously induce navigation heuristics and refine cognitive strategies through a continuous reflection-adaptation loop. By abstracting success patterns and failure pitfalls into natural-language heuristics, Robo-Cortex enables a transition from passive execution to active strategy evolution. Our core innovation is an Autonomous Knowledge Induction (AKI) mechanism that distills multimodal trajectories into a structured Navigation Heuristic Library for knowledge generalization. The architecture further incorporates a Dual-Grain Cognitive Memory system, comprising a Short-term Reflective Memory (SRM) for real-time local progress analysis, and a Long-term Principle Memory (LPM) that abstracts past trajectories into reusable guiding and cautionary principles. To ensure robust decision-making, we introduce a multimodal Imagine-then-Verify loop, where a world model simulates potential outcomes and a VLM-based evaluator validates action plans. Extensive evaluations on IGNav, AR, and AEQA show that Robo-Cortex consistently outperforms strong baselines in both task success and exploration efficiency, with gains of up to +4.16% SPL over the strongest prior method and up to +15.30% SPL under heuristic transfer to unseen environments. Preliminary real-world robotic experiments further support the effectiveness of Robo-Cortex in physical settings.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18729
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
Chan, Nga Teng
Zhang, Yi
Liu, Yechi
Cui, Renwen
Zeng, Fanhu
Ding, Zeyuan
Ren, Xiancong
Zhang, Zhang
Chen, Qifeng
Liu, Jian
Dai, Yong
Ju, Xiaozhu
Robotics
Computer Vision and Pattern Recognition
The ability to navigate and interact with complex environments is central to real-world embodied agents, yet navigation in unseen environments remains challenging due to "experiential amnesia," where existing trajectory-driven or reactive policies fail to synthesize generalizable strategies from past interactions. We propose Robo-Cortex, a self-evolving framework that enables robots to autonomously induce navigation heuristics and refine cognitive strategies through a continuous reflection-adaptation loop. By abstracting success patterns and failure pitfalls into natural-language heuristics, Robo-Cortex enables a transition from passive execution to active strategy evolution. Our core innovation is an Autonomous Knowledge Induction (AKI) mechanism that distills multimodal trajectories into a structured Navigation Heuristic Library for knowledge generalization. The architecture further incorporates a Dual-Grain Cognitive Memory system, comprising a Short-term Reflective Memory (SRM) for real-time local progress analysis, and a Long-term Principle Memory (LPM) that abstracts past trajectories into reusable guiding and cautionary principles. To ensure robust decision-making, we introduce a multimodal Imagine-then-Verify loop, where a world model simulates potential outcomes and a VLM-based evaluator validates action plans. Extensive evaluations on IGNav, AR, and AEQA show that Robo-Cortex consistently outperforms strong baselines in both task success and exploration efficiency, with gains of up to +4.16% SPL over the strongest prior method and up to +15.30% SPL under heuristic transfer to unseen environments. Preliminary real-world robotic experiments further support the effectiveness of Robo-Cortex in physical settings.
title Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.18729