GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions

TL;DR

GraphCoT-VLA is a novel 3D spatial-aware reasoning model for robotic manipulation that effectively interprets ambiguous instructions and models complex interactions, leading to improved success rates and robustness in real-world tasks.

Contribution

The paper introduces a structured reasoning module and a 3D pose-object graph to enhance understanding and manipulation in ambiguous and dynamic environments.

Findings

Significantly outperforms existing methods in success rate

Demonstrates robustness in open environments

Achieves faster response times

Abstract

Vision-language-action models have emerged as a crucial paradigm in robotic manipulation. However, existing VLA models exhibit notable limitations in handling ambiguous language instructions and unknown environmental states. Furthermore, their perception is largely constrained to static two-dimensional observations, lacking the capability to model three-dimensional interactions between the robot and its environment. To address these challenges, this paper proposes GraphCoT-VLA, an efficient end-to-end model. To enhance the model's ability to interpret ambiguous instructions and improve task planning, we design a structured Chain-of-Thought reasoning module that integrates high-level task understanding and planning, failed task feedback, and low-level imaginative reasoning about future object positions and robot actions. Additionally, we construct a real-time updatable 3D Pose-Object graph, which captures the spatial configuration of robot joints and the topological relationships between objects in 3D space, enabling the model to better understand and manipulate their interactions. We further integrates a dropout hybrid reasoning strategy to achieve efficient control outputs. Experimental results across multiple real-world robotic tasks demonstrate that GraphCoT-VLA significantly outperforms existing methods in terms of task success rate and response speed, exhibiting strong generalization and robustness in open environments and under uncertain instructions.