Vehicle Map Consistency Checking for Outdated Road Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles rely on stored maps that may not be updated to reflect changes in the environment, leading to potential safety issues if the maps are inaccurate, such as driving on non-drivable surfaces or incorrect lane positions.
Innovation Solution
The system generates an estimated map in real-time using sensor data from onboard components like lidar and cameras, comparing it to the stored map to determine consistency, and adjusts vehicle navigation accordingly, using redundancy across different sensor modalities to ensure safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the autonomous vehicle uses stored map data for navigation, then the navigation system can operate with pre-planned routes and efficient pathfinding, but the map data may become outdated and inconsistent with the current environment, leading to safety issues
Solution Approach 1:
The system continuously compares sensor data from the current environment with stored map data, detecting inconsistencies and feeding this information back to update the map. This feedback loop ensures map data remains accurate while maintaining efficient navigation using pre-planned routes.
Solution Approach 2:
The system performs preliminary consistency checks by comparing sensor data with stored map data before executing navigation decisions. This preliminary verification ensures that pre-planned routes remain valid and safe to follow.
2Measurement precision
If the autonomous vehicle relies solely on sensor data for real-time environment perception, then the system can accurately detect current environmental conditions, but the navigation decisions may lack the contextual information provided by pre-existing map data
Solution Approach 1:
The system merges sensor data with stored map data to create a comprehensive environmental understanding. By combining real-time detection accuracy with pre-existing contextual information from maps, the system maintains both precise measurement and rich contextual awareness for better navigation decisions.
3Reliability
If the system continuously updates and verifies map consistency using sensor data, then the reliability of navigation information is improved, but the computational load and processing time increase
Solution Approach 1:
The system performs partial consistency checks by focusing on specific regions or features where changes are most likely to occur, rather than verifying the entire map continuously. This selective verification approach maintains high reliability while reducing computational load and processing time.
Data Source
AI summary
Techniques relating to monitoring map consistency are described. In an example, a monitoring component associated with a vehicle can receive sensor data associated with an environment in which the vehicle is positioned. The monitoring component can generate, based at least in part on the sensor data, an estimated map of the environment, wherein the estimated map is encoded with policy information for driving within the environment. The monitoring component can then compare first information associated with a stored map of the environment with second information associated with the estimated map to determine whether the estimated map and the stored map are consistent. Component(s) associated with the vehicle can then control the object based at least in part on results of the comparing.