Map Discrepancy Response Timing Using Encounter Rates and Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in detecting and responding to map discrepancies in real-time, which can impact safety and efficiency, as existing systems lack effective methodologies for determining appropriate Service Level Agreement (SLA) response times and cadence-based review frequencies for map feature errors.
Innovation Solution
The proposed solution involves determining SLA response times based on expected encounter rates and detector precision for map features, and implementing cadence-based review frequencies using a combination of automated and human detectors to ensure timely mitigation of map errors, thereby maintaining system safety and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-time map discrepancy detection is implemented, then safety is improved, but response time determination becomes complex
Solution Approach 1:
The patent applies parameter changes by dynamically adjusting SLA response times based on encounter rates and detector precision. The system calculates different response time thresholds for different map features depending on their encounter frequency and detection accuracy, transforming a complex qualitative safety problem into a quantifiable parameter-based solution that balances safety requirements with operational efficiency
Solution Approach 2:
The patent implements preliminary action by pre-establishing SLA response time thresholds and cadence-based review frequencies before map discrepancies occur. By proactively defining response time requirements based on expected encounter rates and detector precision, the system prepares mitigation strategies in advance, enabling rapid response when actual discrepancies are detected without requiring complex real-time decision-making
2Reliability
If SLA response times are shortened for faster error mitigation, then reliability is improved, but system complexity increases
Solution Approach 1:
The patent applies local quality by implementing differentiated SLA response times for different map features based on their specific encounter rates and detector precision. Rather than applying a uniform response time across all map features, the system tailors response time requirements to local characteristics of each map feature, allowing faster response for critical features while maintaining acceptable response times for less critical features, thereby improving overall reliability without uniformly increasing system complexity
3Measurement precision
If comprehensive map monitoring is implemented, then detection precision is improved, but resource consumption increases
Solution Approach 1:
The patent applies partial action by implementing cadence-based review frequencies that perform comprehensive monitoring at scheduled intervals rather than continuously. The system monitors map features at appropriate frequencies based on their encounter rates and criticality, performing full-scale detection only when necessary while using lighter monitoring between cadence points, thereby maintaining detection precision while reducing overall computational resource consumption
Data Source
AI summary
A methodology is described for determining a time for responding to an initial encounter by a vehicle with a map error in a map segment, wherein the initial encounter is detected by a detector. A method includes identifying an error type associated with the map error, wherein the error type is one of a first error type and a second error type; determining at least one additional factor associated with the initial encounter; determining a response time for the map error based on the error type and the at least one additional factor; and initiating a mitigating action in response to the initial encounter within the response time, wherein the response time comprises an amount of time from the initial encounter with the map error to a time at which a mitigating action should be taken.