# OpenTie: Open-vocabulary Sequential Rebar Tying System

## TL;DR

OpenTie is a versatile, training-free robotic system that uses RGB-to-point-cloud conversion and open-vocabulary detection to accurately tie rebar in various orientations, addressing a gap in existing construction robotics.

## Contribution

The paper introduces OpenTie, a novel 3D, training-free rebar tying framework utilizing RGB-to-point-cloud generation and open-vocabulary detection for flexible construction tasks.

## Key findings

- High accuracy in rebar tying demonstrated in real-world experiments
- Effective handling of both horizontal and vertical rebar tasks
- System operates without prior model training

## Abstract

Robotic practices on the construction site emerge as an attention-attracting manner owing to their capability of tackle complex challenges, especially in the rebar-involved scenarios. Most of existing products and research are mainly focused on flat rebar setting with model training demands. To fulfill this gap, we propose OpenTie, a 3D training-free rebar tying framework utilizing a RGB-to-point-cloud generation and an open-vocabulary detection. We implements the OpenTie via a robotic arm with a binocular camera and guarantees a high accuracy by applying the prompt-based object detection method on the image filtered by our propose post-processing procedure based a image to point cloud generation framework. The system is flexible for horizontal and vertical rebar tying tasks and the experiments on the real-world rebar setting verifies that the effectiveness of the system in practice.