High-Assurance System Design for Autonomous Vehicle Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining suitable physical and software components for autonomous vehicles to ensure safe operation is challenging due to varying reliability and performance attributes, and existing design processes are inefficient and costly.
Innovation Solution
A high assurance design system uses evolutionary and genetic algorithms, combined with expert systems and machine learning, to iteratively adjust candidate systems to meet predefined fitness criteria, such as reliability and performance, by selecting and configuring components from a database.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional design processes are used to determine suitable components for autonomous vehicles, then component selection can be made manually, but the process becomes inefficient and costly
Solution Approach 1:
The patent replaces manual mechanical design processes with an automated computational system that uses machine learning models and algorithms to evaluate component configurations, calculate reliability metrics, and generate optimized system designs automatically, eliminating the need for manual iteration and significantly improving design efficiency
Solution Approach 2:
The system enables self-service by automatically performing component selection, configuration evaluation, and reliability analysis without human intervention. The automated framework independently executes the entire design process from requirements input to final configuration output, reducing both time and cost
2Reliability
If multiple components with varying reliability characteristics are considered to ensure safe operation, then system reliability can be improved, but the complexity of determining suitable component combinations increases
Solution Approach 1:
The patent transforms the complex reliability assessment problem into a standardized computational evaluation by defining specific reliability parameters and metrics that can be automatically calculated and compared across different component configurations, enabling systematic optimization without manual complexity
Solution Approach 2:
The system segments the overall system design into discrete evaluable components, allowing independent assessment of each component's reliability characteristics and their combined effect on system-level reliability, making the complex problem manageable through modular analysis
3Reliability
If exhaustive evaluation of all possible component configurations is performed to ensure safety, then reliability can be maximized, but the computational cost and time required increases significantly
Solution Approach 1:
The patent implements partial action by evaluating a strategically selected subset of component configurations rather than exhaustively analyzing all possible combinations. The system identifies and focuses evaluation resources on the most promising configurations based on initial filtering criteria, achieving sufficient reliability without the prohibitive cost of complete enumeration
Solution Approach 2:
The system performs preliminary filtering and pre-evaluation of component configurations before conducting full reliability analysis. By pre-screening options based on basic criteria and eliminating clearly suboptimal configurations early, the system reduces the computational burden of subsequent detailed evaluation while maintaining reliability guarantees
Data Source
AI summary
Techniques for efficiently generating systems are disclosed herein. Abstract system definitions can define the various functions of a system and/or the fitness requirements of the system. Components capable of implementing the aspects of the abstract system can be determined and systems configured to perform the functions of the abstract system are determined. The fitness of these systems can be evaluated to determine whether they meet the fitness requirements of the abstract system. If not, an algorithm is used to iteratively adjust the configurations and components of the systems until the fitness criteria is met.