Structured Task Solving via Modular Embodied Intelligence: A Case Study on Rubik's Cube

TL;DR

Auto-RubikAI is a modular framework combining symbolic reasoning, vision-language understanding, and large language models to solve Rubik's Cube tasks with high success rates and interpretability, demonstrating effective real-world deployment.

Contribution

The paper introduces Auto-RubikAI, a novel modular system integrating KB, VLM, and LLM for interpretable, minimal-data structured task solving in robotics.

Findings

Achieved 79% success rate in real-world Rubik's Cube solving.

Reduced solution steps compared to baseline methods.

Demonstrated effective sim-to-real transfer without retraining.

Abstract

This paper presents Auto-RubikAI, a modular autonomous planning framework that integrates a symbolic Knowledge Base (KB), a vision-language model (VLM), and a large language model (LLM) to solve structured manipulation tasks exemplified by Rubik's Cube restoration. Unlike traditional robot systems based on predefined scripts, or modern approaches relying on pretrained networks and large-scale demonstration data, Auto-RubikAI enables interpretable, multi-step task execution with minimal data requirements and no prior demonstrations. The proposed system employs a KB module to solve group-theoretic restoration steps, overcoming LLMs' limitations in symbolic reasoning. A VLM parses RGB-D input to construct a semantic 3D scene representation, while the LLM generates structured robotic control code via prompt chaining. This tri-module architecture enables robust performance under spatial uncertainty. We deploy Auto-RubikAI in both simulation and real-world settings using a 7-DOF robotic arm, demonstrating effective Sim-to-Real adaptation without retraining. Experiments show a 79% end-to-end task success rate across randomized configurations. Compared to CFOP, DeepCubeA, and Two-Phase baselines, our KB-enhanced method reduces average solution steps while maintaining interpretability and safety. Auto-RubikAI provides a cost-efficient, modular foundation for embodied task planning in smart manufacturing, robotics education, and autonomous execution scenarios. Code, prompts, and hardware modules will be released upon publication.