OpenTie: Open-vocabulary Sequential Rebar Tying System
This addresses robotic automation challenges in construction rebar tying, though it appears incremental as it builds on existing detection methods with new processing.
The researchers tackled the problem of robotic rebar tying in construction by developing OpenTie, a 3D training-free framework using RGB-to-point-cloud generation and open-vocabulary detection, which achieved high accuracy in real-world experiments for both horizontal and vertical rebar tying tasks.
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.