ScanBot: Towards Intelligent Surface Scanning in Embodied Robotic Systems

TL;DR

ScanBot introduces a high-precision surface scanning dataset for robots, emphasizing the challenges of instruction-following and stability in industrial laser scanning tasks, and benchmarks current models' limitations.

Contribution

The paper presents a new dataset for instruction-guided high-precision surface scanning and evaluates multimodal models' performance in realistic robotic scenarios.

Findings

Existing models struggle with stable, precise scanning trajectories.

Benchmark reveals significant challenges in instruction-following accuracy.

Dataset enables research on fine-grained, real-world robotic perception and control.

Abstract

We introduce ScanBot, a novel dataset designed for instruction-conditioned, high-precision surface scanning in robotic systems. In contrast to existing robot learning datasets that focus on coarse tasks such as grasping, navigation, or dialogue, ScanBot targets the high-precision demands of industrial laser scanning, where sub-millimeter path continuity and parameter stability are critical. The dataset covers laser scanning trajectories executed by a robot across 12 diverse objects and 6 task types, including full-surface scans, geometry-focused regions, spatially referenced parts, functionally relevant structures, defect inspection, and comparative analysis. Each scan is guided by natural language instructions and paired with synchronized RGB, depth, and laser profiles, as well as robot pose and joint states. Despite recent progress, existing vision-language action (VLA) models still fail to generate stable scanning trajectories under fine-grained instructions and real-world precision demands. To investigate this limitation, we benchmark a range of multimodal large language models (MLLMs) across the full perception-planning-execution loop, revealing persistent challenges in instruction-following under realistic constraints.