Three-dimensional hazard analysis method for embodied intelligent mobile robots

By constructing a three-dimensional orthogonal space of scenario, capability, and function, the scenario deviation and capability gap of intelligent mobile robots are quantified, solving the problem that traditional two-dimensional analysis methods cannot quantify AI uncertainty and deep hardware-software coupling failure, and realizing highly reliable safety analysis of robots in open environments.

CN122816283APending Publication Date: 2026-09-25CHINA AERO POLYTECH ESTAB
0 Cites 0 Cited by

Patent Information

Application Number
CN202610977232.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-07-02
Publication Date
2026-09-25

AI Technical Summary

Technical Problem

Existing traditional two-dimensional causal security analysis methods cannot effectively quantify the uncertainty of AI and the failure of deep software and hardware coupling in complex environments, resulting in insufficient security analysis of intelligent mobile robots in open environments.

Method used

Construct a three-dimensional orthogonal mathematical space of scenario, capability, and function. Through a multi-dimensional nonlinear mapping model, realize the closed-loop analysis of the entire link from environmental perception to system control, quantify scenario deviation, capability gap and functional risk, and establish a tracking matrix for safety assessment.

Benefits of technology

Accurately identify safety hazards in complex environments, quantify the degree of risk, improve the safety of robots in open environments, and ensure the physical implementation and high reliability of safety strategies.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a three-dimensional hazard analysis method for a body-integrated intelligent mobile robot, and belongs to the technical field of cross of artificial intelligence and robot system engineering and safety evaluation. Firstly, a system complexity characteristic index is evaluated to trigger an analysis framework and import a running design domain; then, a scene-ability-function three-dimensional orthogonal architecture analysis is performed; finally, a multi-dimensional tracking matrix is used to calculate a system key gap index KGI and a gate access index GPI, a closed-loop safety design baseline is output, and a real-time control strategy of the robot is generated. The application breaks through the limitation of traditional single-point failure evaluation, accurately quantifies the coupling risk of hardware and software, significantly improves the safety confidence of the body-integrated intelligent robot in a real dynamic environment, and can be applied to the safety evaluation scene of an aerial robot, such as aircraft ground support, aircraft maintenance and airport ground collaborative work.
Need to check novelty before this filing date? Find Prior Art