Expected function safety risk assessment method for automatic driving vehicle error/missing identification
A technology for autonomous driving and expected functions, which is applied in vehicle position/route/altitude control, motor vehicles, and non-electric variable control, etc., and can solve problems such as insufficient information about expected functions of autonomous vehicles and uncontrollable operating conditions. Achieve the effect of improving the intended functional safety, reducing risk, ensuring safety and reliability
Active Publication Date: 2021-04-06
AUTOMOBILE RES INST OF TSINGHUA UNIV IN SUZHOU XIANGCHENG +1
View PDF6 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Self-driving vehicles are based on scenarios, and safety is based on the need to put driving safety first. However, the reality is that many drivers do not put driving safety first. The relevant self-driving vehicles provided to drivers The information of the expected function is not clear enough, the uncontrollability of key operating conditions, etc., which will lead to danger, how to reduce the risk to confirm the safety of the expected function of autonomous driving is a challenge for SOTIF
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.
[0033] Such as figure 1 As shown, the anticipatory functional safety risk assessment method for automatic driving vehicle error / missing identification of the present invention includes the following steps:
[0034] S1, analysis of trigger events for false / missing recognition of autonomous vehicles
[0035] Before analyzing the specific trigger events based on false / missing recognition of autonomous driving vehicles, it is necessary to identify potential dangerous behaviors caused by false / missing recognition, and then analyze the triggering events of false / missing recognition by comparing the specific environmental conditions with the expected dangerous scene and the safety scene , as shown in Table 1, mainly includes risk events caused by false / missing identification and corresponding triggering events. For example, the sensor camera recogn...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an expected function safety risk assessment method for automatic driving vehicle error / missing identification, which comprises the following steps: analyzing an automatic driving vehicle error / missing identification trigger event to obtain a reason for triggering the error / missing identification event and an occurrence scene; constructing and testing an automatic driving vehicle error / missing identification simulation test scene in simulation software, and therefore, the influence of error / missing identification on expected function safety is improved; uploading the functional performance limitation of the system / component of the automatic driving vehicle caused by error / missing identification to a cloud management system for storage; and performing severe grading on functions with limited performance, and analyzing potential occurrence frequency and detectable degree so as to take corresponding measures. According to the invention, the expected function safety of error / missing identification of the automatic driving vehicle can be effectively and reasonably improved, the risk caused by insufficient system performance is reduced, and the safety and reliability of the automatic driving vehicle are ensured.
Description
technical field [0001] The invention relates to the technical field of unmanned driving testing, in particular to a method for assessing the risk of expected functional safety for automatic driving vehicle error / missing identification. Background technique [0002] Self-driving vehicles are designed to solve the unsafe problem of human driving. According to NHTSA (U.S. Department of Transportation Highway Safety Administration) statistics, about 25,000 people die on U.S. highways every year, and 94% of them are caused by the ineffective driving function caused by the driver. However, automatic driving will produce safety problems that new human drivers do not have—Unknown (unknown), Unsafety (unsafe), that is, the expected functional safety SOTIF. Anticipated functional safety SOTIF emphasizes avoiding unreasonable risks due to expected functional performance limitations and insufficient performance. That is to say, when all the functions of the vehicle do not fail, the dr...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G05D1/02
CPCG05D1/0246G05D1/0257G05D1/0214G05D1/0221G05D1/0276
Inventor 李茹马育林田欢孙川郑四发
Owner AUTOMOBILE RES INST OF TSINGHUA UNIV IN SUZHOU XIANGCHENG