Autonomous Vehicle HD Map Updates via Lane Closure Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional maps for autonomous vehicles lack precision and accuracy, are expensive to maintain, and fail to keep up with frequent changes in road conditions, leading to unsafe navigation due to outdated data.
Innovation Solution
A computer-implemented method for generating and updating high-definition maps using sensor data from autonomous vehicles, which detects lane closures and openings, and an online system that processes this data to provide real-time, accurate map updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional maps are used for autonomous vehicle navigation, then the system can operate with existing infrastructure, but the maps lack sufficient precision and accuracy for safe navigation
Solution Approach 1:
The system enables autonomous vehicles to self-update the HD maps by detecting lane closures and openings using their own sensors. The vehicles autonomously generate map updates and transmit them to the server, eliminating the need for manual survey teams and achieving high precision maps through vehicle fleet participation rather than complex manual survey operations.
Solution Approach 2:
The patent replaces the mechanical survey process (survey cars with high resolution sensors driven by humans) with an automated electronic system where autonomous vehicles use their onboard sensors (cameras, LIDAR) to detect road changes and electronically transmit data to update HD maps, substituting manual mechanical surveying with automated sensor-based detection and communication.
2Measurement precision
If manual survey teams create HD maps, then maps can be detailed, but the process is expensive and time-consuming
Solution Approach 1:
The system enables continuous map updates as autonomous vehicles traverse the road network, detecting and reporting lane changes in real-time. This continuous action replaces the periodic manual survey process, ensuring maps are constantly updated with current road conditions without the time delays associated with scheduling and executing manual survey missions.
Solution Approach 2:
The system establishes a feedback loop where autonomous vehicles continuously monitor road conditions, compare them against the HD map, detect discrepancies (lane closures/openings), and transmit correction data back to the server. This feedback mechanism enables rapid map updates based on actual observed conditions, eliminating the time loss of manual survey coordination.
3Adaptability or versatility
If conventional maps are used, then infrastructure can be leveraged, but the maps become outdated faster than they can be updated
Solution Approach 1:
The system performs preliminary detection of lane changes by having autonomous vehicles continuously monitor road conditions and identify changes before they affect navigation. By detecting lane closures and openings early and transmitting update requests proactively, the system maintains map freshness and enables faster updates compared to reactive manual surveying.
Solution Approach 2:
The map update system transitions from a static, periodic manual survey model to a dynamic, event-driven continuous update model. Maps are updated in real-time based on detected road changes rather than following a fixed survey schedule, enabling the system to adapt to changing road conditions at any moment and maintain high map freshness.
4Area of stationary object
If survey fleets are deployed to cover large areas, then comprehensive map coverage can be achieved, but the cost and complexity increase significantly
Solution Approach 1:
The system makes autonomous vehicles universal map update participants, allowing any autonomous vehicle in the fleet to contribute to HD map updates regardless of its primary function. Vehicles perform multiple functions: navigation, sensor data collection, and map maintenance, eliminating the need for dedicated survey fleets and reducing overall system complexity while maintaining comprehensive coverage.
Solution Approach 2:
The patent merges the map survey function with the autonomous vehicle navigation function. Instead of having separate survey vehicles and navigation vehicles, the system combines both functions into a single autonomous vehicle platform, where the navigation task inherently includes map update participation, thereby reducing fleet complexity and costs.
Data Source
AI summary
A computer-implemented method may comprise: receiving sensor data from a sensor of an autonomous vehicle; determining a presence of a lane closure object located on a lane element; determining a change of the lane closure object, selected from the presence of the lane closure object or absence of the lane closure object on the lane element; generating a change candidate based on the change in the lane closure object; obtaining a plurality of the change candidates during a time period or the autonomous vehicle being on a preceding lane element on the route; analyzing the plurality of change candidates for the change being the presence of the lane closure object or the absence of the lane closure object on the lane element; generating a final change candidate based on the change; and providing the final change candidate for updating a high definition map of the route having the lane element.