Hume: Introducing System-2 Thinking in Visual-Language-Action Model

TL;DR

Hume introduces a dual-system approach combining slow, value-guided reasoning with fast reactive control in a vision-language-action model to enhance dexterous robot manipulation in physical environments.

Contribution

The paper presents Hume, a novel dual-system VLA model incorporating System-2 value-guided thinking and cascaded action denoising for improved robotic dexterity.

Findings

Hume outperforms existing models in simulation benchmarks.

Hume achieves superior real-robot dexterous control.

System-2 thinking enhances decision accuracy in complex tasks.

Abstract

Humans practice slow thinking before performing actual actions when handling complex tasks in the physical world. This thinking paradigm, recently, has achieved remarkable advancement in boosting Large Language Models (LLMs) to solve complex tasks in digital domains. However, the potential of slow thinking remains largely unexplored for robotic foundation models interacting with the physical world. In this work, we propose Hume: a dual-system Vision-Language-Action (VLA) model with value-guided System-2 thinking and cascaded action denoising, exploring human-like thinking capabilities of Vision-Language-Action models for dexterous robot control. System 2 of Hume implements value-Guided thinking by extending a Vision-Language-Action Model backbone with a novel value-query head to estimate the state-action value of predicted actions. The value-guided thinking is conducted by repeat sampling multiple action candidates and selecting one according to state-action value. System 1 of Hume is a lightweight reactive visuomotor policy that takes System 2 selected action and performs cascaded action denoising for dexterous robot control. At deployment time, System 2 performs value-guided thinking at a low frequency while System 1 asynchronously receives the System 2 selected action candidate and predicts fluid actions in real time. We show that Hume outperforms the existing state-of-the-art Vision-Language-Action models across multiple simulation benchmark and real-robot deployments.