Collision Scenario Data Reliability via Dual-Risk Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The reliability of collision scenario data collected from witness statements is low, affecting the performance of autonomous driving perception and decision-making algorithms, as well as vehicle abnormality diagnosis and accident liability determination.
Innovation Solution
A method that involves obtaining scenario data using perception and driving sensors, calculating collision risk scores for perception and driving data, and determining a collision confidence level to objectively identify collision scenario data, thereby improving data reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual collection of witness statements is used, then collection simplicity is maintained, but data reliability deteriorates
Solution Approach 1:
The patent replaces manual witness statement collection with an automated detection system that uses perception data and driving data processing. The system automatically calculates collision risk scores and determines collision confidence levels, eliminating the need for manual witness interviews while significantly improving data reliability and objectivity.
Solution Approach 2:
The system enables self-service by automatically detecting and identifying collision scenarios using onboard sensors and processing units. The collision detection system independently analyzes perception data and driving data to determine collision confidence levels without requiring external manual intervention or witness statements.
2Measurement precision
If witness statements are collected, then collection process is simple, but measurement precision deteriorates
Solution Approach 1:
The patent replaces manual witness statement collection with an automated detection system that uses perception data and driving data processing. The system automatically calculates collision risk scores and determines collision confidence levels, eliminating the need for manual witness interviews while significantly improving data reliability and objectivity.
Solution Approach 2:
The system incorporates feedback mechanisms by continuously monitoring collision confidence levels and using this information to determine whether a scenario qualifies as a collision. The feedback loop ensures that only scenarios meeting the predefined confidence threshold are classified as collisions, improving measurement precision through objective, data-driven determination.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
The disclosure provides a method for detecting collision data, a driving device and a medium. The method includes: obtaining scenario data that includes perception data about a surrounding target object and driving data of the object to be detected; calculating a collision risk score based on the perception data and the driving data separately to obtain a first collision risk score for the perception data and a second collision risk score for the driving data; obtaining a collision confidence level for the scenario data based on the first collision risk score and the second collision risk score; and if the collision confidence level is greater than a preset confidence threshold, determining the scenario data as collision scenario data, and/or recalling the scenario data, thereby realizing objective collection of the collision scenario data with a higher collision confidence level, and improving the reliability of the collision scenario data, thus helping improve the performance of autonomous driving perception and decision-making algorithms, and improving the reliability of vehicle abnormality diagnosis, accident liability determination, etc.