Onboard Road Obstacle Detection for Virtual Stop Line Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle navigation systems struggle to incorporate unobservable road features, such as unmarked intersections and proper yield positions, into maps, which are crucial for safe navigation and collision avoidance.
Innovation Solution
A map creation and update framework that uses on-board data processing systems in vehicles to identify potential vehicle stops, classify situations using AI, and generate virtual stop or yield lines, which are then aggregated and validated by external systems to update maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If vehicles use traditional map data for navigation, then navigation systems are simple and easy to maintain, but they cannot identify unobservable road features like unmarked intersections and yield positions
Solution Approach 1:
The system enables vehicles to autonomously identify unobservable road features through onboard sensors and AI processing, and automatically contribute this information to map updates without requiring manual mapping efforts. Vehicles serve themselves by detecting features and simultaneously serving the broader system by sharing data for collective map improvement
Solution Approach 2:
An external system acts as an intermediary that receives virtual stop line data from multiple vehicles, aggregates and validates the information, and distributes updated map data back to vehicles. This mediator coordinates the complex interactions between numerous vehicles and the central map database, managing the flow of information and ensuring data quality
2Measurement precision
If vehicles transmit detailed sensor data to external systems, then map accuracy improves, but data transmission volume increases and user privacy is compromised
Solution Approach 1:
The system extracts only the essential information needed for map updates—specifically virtual stop line locations and characteristics—separating this critical data from the vast amount of raw sensor data. By transmitting only the extracted relevant information rather than complete sensor datasets, the system achieves high measurement precision while minimizing data transmission volume and energy consumption
Solution Approach 2:
Vehicles perform preliminary processing of sensor data onboard using AI models to identify and classify stop events before transmission. This preliminary action filters and structures data in advance, ensuring that only validated, high-quality virtual stop line information is transmitted to external systems, thereby improving identification precision while reducing unnecessary data transmission
3Measurement precision
If vehicles transmit detailed sensor data to external systems, then map accuracy improves, but data transmission volume and user privacy concerns increase
Solution Approach 1:
The system extracts and transmits only the minimal necessary information for map improvement—virtual stop line geometric and contextual data—while deliberately excluding any personally identifiable information or sensitive user behavior patterns. This selective extraction maintains measurement precision for road feature identification while preserving user privacy by not collecting or transmitting unnecessary personal data
4Ease of operation
If vehicles frequently stop and start in stop-and-go traffic, then navigation responds to traffic conditions, but fuel consumption increases
Solution Approach 1:
The system performs preliminary identification of virtual stop lines and traffic patterns in advance, allowing vehicles to anticipate upcoming stops and optimize acceleration and deceleration strategies. By knowing stop locations beforehand through accurate map data, vehicles can plan energy-efficient trajectories rather than reacting abruptly to traffic conditions, reducing fuel consumption while maintaining responsive navigation
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.