Vehicle Obstacle Mapping Using AI-Derived Virtual Stop Lines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle systems struggle to incorporate unobservable road features, such as unmarked intersections and yield points, into navigation maps, which can lead to collisions and inefficient navigation.
Innovation Solution
A vehicle-based system that uses on-board sensors and artificial intelligence to detect vehicle stops, classify situations, and generate virtual stop or yield lines, which are then aggregated and validated by an external system to update maps, allowing for the inclusion of unobservable road features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If vehicles use traditional map data for navigation, then navigation systems are simple and easy to maintain, but unobservable road features like unmarked intersections cannot be identified leading to collisions and inefficient navigation
Solution Approach 1:
The system enables vehicles to autonomously identify and map unobservable road features using their own sensors and AI processing capabilities. Each vehicle serves itself by detecting stop locations, classifying situations with neural networks, and contributing to collective map updates without requiring complex centralized infrastructure
Solution Approach 2:
An external system acts as an intermediary to aggregate stop location data from multiple vehicles, cluster them to identify representative virtual stop lines, validate against existing map data, and update maps. This mediator coordinates the complex interactions between numerous vehicles and the mapping infrastructure
2Measurement precision
If vehicles autonomously generate virtual stop lines at every detected stop location, then unobservable road features are captured in detail, but data redundancy increases requiring aggregation and validation
Solution Approach 1:
The system segments the map update process into distinct stages: individual vehicles detect and generate virtual stop lines, external systems aggregate and cluster data from multiple vehicles, validate against existing maps, and apply updates. This segmentation allows precise local measurements while managing overall data volume through hierarchical processing
Solution Approach 2:
Multiple vehicles' stop location data are merged and clustered by the external system to identify representative virtual stop lines. By combining data from multiple sources and applying clustering algorithms, the system achieves comprehensive coverage while reducing redundancy through consolidation
Data Source
AI summary
A vehicle can include an on-board data processing system that receives sensor data captured by various sensors of the vehicle. As a vehicle travels along a route, the on-board data processing system can process the captured sensor data to identify a potential vehicle stop. The on-board data processing system can then identify geographical coordinates of the location at which the potential vehicle stop occurred, use artificial intelligence to classify a situation of the vehicle at the potential stop, and determine whether the stop was caused by a road obstacle, such as a speed bump, a gutter, an unmarked crosswalk, or any other obstacle not at an intersection. If the stop was caused by the road obstacle, the on-board data processing system can generate virtual stop or yield line data corresponding to the identified geographic coordinates and transmit this data to a server over a network for processing.