Zero-Shot Robotic Manipulation via 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation

TL;DR

The results validate that RobMRAG effectively bridges the gap between high-level semantic reasoning and low-level geometric execution, enabling robotic systems that generalize to unseen objects while remaining inherently interpretable.

Abstract

Existing end-to-end approaches of robotic manipulation often lack generalization to unseen objects or tasks due to limited data and poor interpretability. While recent Multimodal Large Language Models (MLLMs) demonstrate strong commonsense reasoning, they struggle with geometric and spatial understanding required for pose prediction. In this paper, we propose RobMRAG, a 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation (MRAG) framework for zero-shot robotic manipulation. Specifically, we construct a multi-source manipulation knowledge base containing object contact frames, task completion frames, and pose parameters. During inference, a Hierarchical Multimodal Retrieval module first employs a three-priority hybrid retrieval strategy to find task-relevant object prototypes, then selects the geometrically closest reference example based on pixel-level similarity and Instance Matching Distance (IMD). We further introduce a 3D-Aware Pose Refinement module based on 3D Gaussian Splatting into the MRAG framework, which aligns the pose of the reference object to the target object in 3D space. The aligned results are reprojected onto the image plane and used as input to the MLLM to enhance the generation of the final pose parameters. Extensive experiments show that on a test set containing 30 categories of household objects, our method improves the success rate by 7.76% compared to the best-performing zero-shot baseline under the same setting, and by 6.54% compared to the state-of-the-art supervised baseline. Our results validate that RobMRAG effectively bridges the gap between high-level semantic reasoning and low-level geometric execution, enabling robotic systems that generalize to unseen objects while remaining inherently interpretable.

Figures (5)

• Figure 1: (a) Although multimodal large language models (MLLMs) possess the commonsense knowledge that opening a drawer requires grasping the handle and can roughly localize it, the predicted 2D contact points consistently fall outside the table itself, let alone on the handle. (b) We incorporate contact pose prediction using a multimodal retrieval-augmented generation (MRAG) framework. By retrieving relevant manipulation examples, our method enables more accurate inference of the contact pose on the target object.
• Figure 2: Overview of the RobMRAG: a 3D Gaussian splatting-enhanced multimodal retrieval-augmented generation framework.
• Figure 3: Ablation study on the number of retrieval candidates (Top-n) and rotation samples (K).
• Figure 4: Visualization of the three-priority hybrid retrieval strategy: ① sparse retrieval (simulation), ② dense retrieval (simulation), and ③ cross-source retrieval (robotic/Internet).
• Figure 5: Visualization of 3D-Aware Pose Refinement.