GB/T 45579-2025Evaluation and grading of robot intelligent vision (English PDF)

Foreword

This document is in accordance with the provisions of GB/T 1.1-2020 "Guidelines for standardization work Part

1.Structure and drafting rules for standardization documents" Drafting. Please note that some of the contents of this document may involve patents. The issuing organization of this document does not assume the responsibility for identifying patents. This document was proposed by the China Machinery Industry Federation. This document is under the jurisdiction of the National Technical Committee on Robotics Standardization (SAC/TC591). This document was drafted by: Shanghai Robotics Industry Technology Research Institute Co., Ltd., JEKA Robotics Co., Ltd., Guangdong Bozhilin Machinery Co., Ltd., Midea Group (Shanghai) Co., Ltd., Shanghai SAZHI Intelligent Technology Co., Ltd., FAOYIWEI (Suzhou) Robotics System Co., Ltd. Co., Ltd., Shanghai Qinglang Intelligent Technology Co., Ltd., Beijing Lobid Technology Co., Ltd., Qiyuan Laboratory, China Mobile (Hangzhou) Information Technology Co., Ltd. Company, Shanghai Electric Science Research Institute (Group) Co., Ltd., Shanghai Guoping Intelligent Inspection Robot Co., Ltd., Weikai Testing Technology Co., Ltd., East China Normal University, Ecovacs Robotics Co., Ltd., Bangkece (Shanghai) Intelligent Medical Technology Co., Ltd., Shanghai Zhongxun Technology Co., Ltd. Co., Ltd., Synade Technology Co., Ltd., Suzhou Mingtu Intelligent Technology Co., Ltd., Sichuan Blue Ocean Intelligent Equipment Manufacturing Co., Ltd., Hukezhi Energy Technology (Shanghai) Co., Ltd., Chongqing Kairui Certification Service Co., Ltd., Shanghai Turing Intelligent Manufacturing Robot Co., Ltd., Chongqing Kairui Robot Robotics Technology Co., Ltd., Jiangsu Huibo Robotics Technology Co., Ltd., Shanghai Betterway Automation Technology Co., Ltd., Yangtze River Delta Hart Robotics Industry Technology Research Institute. The main drafters of this document are. Zheng Junqi, Xu Xiong, Hu Jiawen, Feng Feifei, Zhang Jianzheng, Wang Chao, Tang Xuanlai, Huo Xiang, Liang Bin, Xia Yi, Xing Lin, Fan Jiaqi, Xing Jun, Qiu Song, Yan Hai, Meng Xiang, Zhang Zhaodong, Wang Mingqiu, Li Hua, Lv Xinwei, Lan Bing, Jiang Hui, Tang Chenyu, Zhou Junjie, Wang Yuqin, Yu Xinchen, Chen Hongguang, and Zhao Lijun. Robot intelligent vision evaluation method and classification

1 Scope

China's national standard for evaluating and grading robot intelligent vision. Vision is what separates a robot that repeats a taught path from one that responds to what is in front of it, and the capability now spans an enormous range - from a camera that locates a part in a fixture to a system that recognises unfamiliar objects, estimates their pose, and plans a grasp. Buyers have no way to compare across that range, because every supplier describes its system as intelligent and the demonstrations are staged. A graded scale, with defined evaluation conditions and methods, is what makes the claim checkable. The standard specifies the general principles, the classification of visual intelligence levels and the evaluation conditions, and describes the evaluation methods, result calculation and reporting. It applies to industrial robots, personal and household service robots, public service robots and special robots led by construction robots, and excludes medical, military, toy and unmanned aerial applications.

This document specifies the general principles, visual intelligence level classification, and evaluation conditions for robot intelligent vision evaluation, and describes the corresponding evaluation methods. Method, result calculation and evaluation report. This document applies to industrial robots, personal/household service robots, public service robots, special robots (mainly construction robots Intelligent visual evaluation and grading of humans) for reference by other types of special robots. This document does not apply to medical robots, military robots, toys with robotic features, or unmanned aerial vehicles.

2 Normative references

The contents of the following documents constitute essential clauses of this document through normative references in this document. For referenced documents without a date, only the version corresponding to that date applies to this document; for referenced documents without a date, the latest version (including all amendments) applies to This document.

GB/T 2423.10 Environmental testing Part

3 Terms and definitions

The following terms and definitions apply to this document.

3.1 robot A programmable mechanism with a certain degree of autonomy to perform movement, manipulation or positioning. Note 1 to entry. A robot includes a control system. Note

2.Examples of robot mechanical structures are manipulators, mobile platforms and wearable robots. [Source: GB/T 12643-2025, 3.1]

3.2 The robot's perception, cognition, decision-making and other functions can realize autonomous operation in unstructured or dynamic environments.

3.3 Robotic Vision System Through multimodal visual sensing, images or videos of the target environment are collected and analyzed to obtain relevant information about the target object.