Autonomous Vehicle Map Updating From Sensor-Detected Inconsistencies
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems face challenges in accurately perceiving and predicting the driving environment due to outdated navigational maps, which can lead to unsafe navigation when inconsistencies between sensor data and map data occur.
Innovation Solution
A control system for autonomous vehicles that uses sensor data to detect inconsistencies, trigger real-time mapping of the driving environment, and update the navigational map, employing an anomaly detection module and a real-time mapping module to ensure accurate route information and safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If real-time mapping is triggered frequently to update navigational maps, then map accuracy is improved, but computational resource consumption increases
Solution Approach 1:
The system performs partial mapping updates by only processing areas where inconsistencies are detected between sensor data and existing map data, rather than performing complete real-time mapping. This selective approach triggers comprehensive real-time mapping only when a threshold number of inconsistencies are detected, thereby improving map accuracy in critical areas while conserving computational resources.
2Measurement precision
If comprehensive real-time mapping is performed continuously, then navigational map accuracy is improved, but processing time increases
Solution Approach 1:
The system implements periodic inconsistency detection at scheduled intervals and event-triggered detection when specific conditions are met. Comprehensive real-time mapping is performed periodically or when a threshold of inconsistencies is reached, rather than continuously. This periodic approach ensures map accuracy is maintained while avoiding the excessive processing time associated with continuous mapping operations.
3Measurement precision
If real-time mapping is triggered for every detected inconsistency, then map accuracy is improved, but system response time increases
Solution Approach 1:
The system applies a threshold-based triggering mechanism where real-time mapping is only initiated when the number of detected inconsistencies exceeds a predetermined threshold. For inconsistencies below the threshold, the system continues using existing map data without triggering comprehensive mapping. This partial action approach maintains map accuracy for significant deviations while preserving system response time by avoiding unnecessary mapping operations for minor inconsistencies.
Data Source
AI summary
Systems and methods for updating navigational maps based using at least one sensor are provided. In one aspect, a control system for an autonomous vehicle, includes a processor and a computer-readable memory configured to cause the processor to: receive output from at least one sensor located on the autonomous vehicle indicative of a driving environment of the autonomous vehicle, retrieve a navigational map used for driving the autonomous vehicle, and detect one or more inconsistencies between the output of the at least one sensor and the navigational map. The computer-readable memory is further configured to cause the processor to: in response to detecting the one or more inconsistencies, trigger mapping of the driving environment based on the output of the at least one sensor, update the navigational map based on the mapped driving environment, and drive the autonomous vehicle using the updated navigational map.