Quantitative loading assisting method and system based on radar scanning and deep learning

By combining dual-radar collaborative scanning with deep learning, three-dimensional data of the carriage is obtained, which solves the problem of insufficient carriage shape modeling in existing technologies, realizes high-precision quantitative loading control, and improves loading efficiency and safety.

CN121883570BActive Publication Date: 2026-07-10SHANDONG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHANDONG UNIV
Filing Date
2026-03-19
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing quantitative loading technology is difficult to adapt to various vehicle types, cannot fully acquire the three-dimensional structure of the vehicle compartment, and is difficult to capture vehicle movement with high precision. It also lacks collaborative modeling of vehicle compartment geometry, loading progress, and target deviation, resulting in uneven loading and safety issues.

Method used

The system employs dual radars to scan front and rear simultaneously to acquire point cloud data, combines deep learning algorithms to identify key feature locations, and uses point cloud processing algorithms to calculate the dimensions of the carriage and the distance the vehicle moves, thereby achieving dynamic loading control.

Benefits of technology

It achieves accurate measurement of carriage dimensions and efficient detection of vehicle movement distance, improving loading efficiency and safety, adapting to multiple vehicle types and complex environments, reducing the risk of manual intervention, and avoiding overloading and underloading.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121883570B_ABST
    Figure CN121883570B_ABST
Patent Text Reader

Abstract

This invention belongs to the field of quantitative loading technology. It proposes a quantitative loading assistance method and system based on radar scanning and deep learning. The method involves synchronously acquiring the original point cloud data of the vehicle compartment using forward and backward scanning radars arranged along the vehicle's movement direction. After denoising, coarse registration, and ICP fine registration, a high-precision registered point cloud is generated. The point cloud is projected onto the Y-O-Z plane and enhanced, then input into a deep learning model to identify the pixel coordinates of the rear baffle, front baffle, and unloading port. Combined with the actual dimensions of the vehicle compartment, a pixel-to-actual distance mapping coefficient is calculated. The vehicle's movement distance is calculated by weighting the point cloud coordinate displacement and image pixel displacement. Furthermore, based on the vehicle compartment's geometry, dynamic decay of loading progress, and loading deviation, a dynamic correction coefficient for quantitative loading is constructed, and the unloading speed and vehicle movement speed are adjusted in real time accordingly. This achieves multi-vehicle adaptive, high-precision, and fully automated quantitative loading.
Need to check novelty before this filing date? Find Prior Art