Autonomous Sensor Redundancy Risk Boundaries in Real Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems face challenges in determining the capability boundary and associated risk of safety redundancy systems in real-time, which is crucial for ensuring vehicle safety, especially in Level 4 autonomous vehicles operating within defined operational design domains.
Innovation Solution
A method is developed to determine the capability boundary of a safety redundancy autonomous driving vehicle by estimating zone failure risks of sensors using statistical operational data, calculating the Mean Time Between Failure (MTBF) for each sensor, and adjusting risks dynamically based on sensor performance and environmental factors, thereby assessing the reliability of the sensor system for safe autonomous driving.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If redundant and diversified sensors, hardware and algorithms are used to enhance autonomous system capability, then system reliability is improved, but device complexity and cost increase
Solution Approach 1:
The patent segments the autonomous driving system into distinct capability levels (primary system, fallback system, minimum risk condition) and evaluates each separately. This segmentation allows the system to manage complexity by treating different sensor subsets and functional capabilities as distinct evaluable units rather than as a monolithic complex system.
Solution Approach 2:
The patent changes the evaluation parameter from static system capability assessment to dynamic real-time capability boundary determination. By continuously monitoring and re-evaluating sensor functionality, system capability, and risk levels in real-time, the system adapts to changing conditions without requiring permanent over-provisioning of resources.
2Reliability
If real-time monitoring and dynamic risk adjustment are implemented, then safety and reliability are improved, but computational load and processing time increase
Solution Approach 1:
The patent implements partial monitoring by focusing computational resources on critical capability boundaries and risk factors rather than continuously analyzing all system parameters. The system monitors only the essential elements needed to determine capability boundaries and assess risks, avoiding unnecessary computational overhead from comprehensive continuous analysis of all sensors and subsystems.
3Reliability
If capability boundary determination and risk assessment are performed continuously, then operational safety is improved, but system response time and processing overhead increase
Solution Approach 1:
The patent implements periodic capability boundary determination and risk assessment at defined evaluation intervals rather than continuous real-time analysis. This periodic approach allows the system to maintain operational safety by regularly updating capability boundaries and risk assessments while avoiding the processing overhead and response time penalties of continuous monitoring, thus resolving the contradiction between safety and processing efficiency.
Data Source
AI summary
In one embodiment, method for determining capability boundary of a safety redundancy of an autonomous driving vehicle (ADV) includes obtaining a sensor layout associated with the ADV representing a system having a plurality of sensors mounted on a plurality of locations of the ADV. A zone failure risk of one or more sensors within the predetermined zones is estimated based on statistical operational data of the one or more sensors for each of the plurality of predetermined zones. An overall failure risk of the sensors is determined based on the zone failure risks of the predetermined zones based on relative locations of the sensors across the predetermined zones. A dynamic risk adjustment is determined based on the overall failure risk of the sensors, the dynamic risk adjustment representing a reliability of a sensor system associated with the ADV for estimating a safety of autonomous driving of the ADV.