A High-Precision Perception Framework for Robotic Grasping Based on 3D Point Cloud Pose Estimation

Abstract

Achieving high-precision perception is a critical prerequisite for autonomous robotic grasping, yet balancing geometric accuracy with the low-latency demands of closed-loop control remains an inherent challenge in unstructured environments. This paper proposes a robust, hierarchical 3D pose estimation framework designed to bridge this gap through a coarse-to-fine registration strategy. The pipeline integrates a lightweight YOLOv11 detector with a multi-stage refinement process. Experiments on the HV8 industrial dataset demonstrate that the detector achieves an Average Precision of 0.98, ensuring reliable Region of Interest (ROI) extraction even under significant clutter. For pose initialization, a specialized PointNet architecture provides a preliminary estimate in 0.02 s, effectively bounding positional and rotational errors to 1.38 mm and 3.64 ° , respectively. The final refinement employs an Iterative Closest Point (ICP) algorithm enhanced by Density-Based Spatial Clustering of Applications with Noise (DBSCAN), which suppresses sensor outliers and achieves a registration overlap of 95.01%. Quantitatively, the framework yields a registration Root Mean Square Error (rRMSE) of 2.89 mm, statistically comparable to the global Go-ICP baseline while reducing computational latency by several orders of magnitude. Specifically, the system completes the perception loop in 0.26 s, facilitating real-time feasibility. Furthermore, systematic bin-picking trials substantiate the operational reliability of the framework, achieving an average cycle time of 12.6 s per part. These results confirm the frameworks efficacy for high-speed, high-precision industrial manipulation.