Autonomous Driving Risk Estimation Using Manual Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems face challenges in accurately assessing accident risks due to the complexity of driving scenarios, leading to insufficient testing and potential safety issues, as existing methods require extensive testing miles to ensure software sophistication and safety.
Innovation Solution
A computer-implemented method that monitors driving parameters during autonomous driving, determines autonomous-driving quality, associates it with manual-driving quantities, and calculates an autonomous-driving accident rate value, allowing for software enhancement without real accidents, by leveraging similarities in driver and AI responses to dangerous situations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If extensive autonomous driving testing is conducted to ensure software safety and sophistication, then the reliability of the autonomous driving system is improved, but the time and resources required for testing increase significantly
Solution Approach 1:
The patent applies preliminary action by using manually driven vehicle data to pre-establish accident rate baselines and driving behavior patterns before autonomous testing. This allows the system to predict expected accident rates for autonomous driving scenarios without requiring extensive actual autonomous testing, thereby reducing testing time while maintaining reliability assessment accuracy
Solution Approach 2:
The patent uses copying by creating virtual representations of manual driving behaviors and accident patterns from manually driven vehicles. These copied data patterns are then applied to assess autonomous driving safety, allowing the system to evaluate software reliability without requiring proportional extensive autonomous testing miles
2Reliability
If the autonomous driving software is enhanced to handle complex driving situations correctly, then the accident risk is reduced, but the engineering time and complexity increase
Solution Approach 1:
The patent implements feedback by continuously comparing autonomous driving quantities against manually established accident rate baselines. This feedback mechanism identifies specific situations where the autonomous software performs poorly relative to manual driving standards, allowing targeted software enhancements rather than comprehensive complex redesign
Solution Approach 2:
The patent applies parameter changes by adjusting software behavior based on quantified deviations from safe driving patterns identified through manual data analysis. Rather than increasing overall software complexity, the system modifies specific operational parameters to align with proven safe driving behaviors
3Measurement precision
If manual driving data from multiple vehicles is used to establish accident rate baselines, then the measurement precision of autonomous driving risk assessment is improved, but the data processing complexity increases
Solution Approach 1:
The patent applies merging by consolidating driving data from multiple manually driven vehicles into unified accident rate baselines and behavioral patterns. This combined data set improves measurement precision for autonomous risk assessment while the patent manages the resulting processing complexity through systematic aggregation methods
Data Source
AI summary
A method for estimating an accident risk of an autonomous driving unit produces helpful results with fewer autonomous driving cycles. From driving values, which have been determined from monitoring at least one driving parameter of the driving unit during autonomous driving, an autonomous-driving quantity is determined quantifying an autonomous-driving quality of the driving of the driving unit. The autonomous-driving quantity is associated with a plurality of manual-driving quantities, which have been determined from the same driving parameter during manual driving periods of different driving units. An autonomous-driving accident rate value is determined from accident rate values associated to those manual-driving quantities.