Binding Point Recognition and Localization and Manipulator Binding Path Planning for a Rebar Binding Robot

TL;DR

This paper introduces a rebar binding robot system that improves binding-point recognition and path planning for efficient and accurate automated rebar binding in construction.

Contribution

The paper proposes an integrated method combining a lightweight vision model and an improved RRT-Connect algorithm for rebar binding tasks.

Findings

The YOLOv8n-pose-Binding model improves keypoint detection accuracy and real-time performance with reduced computational complexity.

The improved RRT-Connect algorithm shows better path planning efficiency and path quality in rebar mesh environments.

Simulation and experiments confirm stable improvements in recognition accuracy and inference efficiency over baseline models.

Abstract

Rebar binding is a labor-intensive and low-efficiency process in the production of reinforced concrete prefabricated components, in which consistent binding quality is difficult to guarantee. To address the engineering challenges faced by rebar binding robots in complex construction environments—particularly in terms of binding-point recognition accuracy, real-time performance, and manipulator path planning efficiency—this paper presents an integrated method for binding-point recognition, localization, and binding path planning tailored to rebar binding tasks. First, based on the YOLOv8n-pose architecture, a lightweight rebar binding-point recognition and localization model, termed YOLOv8n-pose-Binding, is developed by introducing multi-scale Ghost convolution structures and an adaptive threshold focal loss. The proposed model improves keypoint detection accuracy and real-time performance while effectively reducing computational complexity, making it suitable for deployment on resource-constrained mobile robotic platforms. Second, a dedicated target coordinate system for rebar binding points is constructed to enable accurate pose estimation in the manipulator base frame. Furthermore, considering the non-uniform obstacle distribution in rebar mesh environments and the high-dimensional motion characteristics of robotic manipulators, systematic improvements are introduced to the RRT-Connect framework from the perspectives of sampling strategies, tree expansion, node reconnection, and path pruning, resulting in an improved RRT-Connect path planning algorithm. Simulation and experimental results demonstrate that, while maintaining favorable real-time performance, the proposed method achieves stable improvements in recognition accuracy and inference efficiency compared with the baseline YOLOv8n-pose model. In addition, the improved RRT-Connect algorithm exhibits superior engineering performance in terms of path planning efficiency and path quality, providing a deployable technical solution for automated rebar binding operations.

Figures