Vehicle Sensor Map Matching for Reliable Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle location methods face challenges due to the absence of prominent topographical objects, adverse weather conditions, outdated third-party maps, and erroneous GPS information, which affect the reliability and accuracy of automated driving assistance systems.
Innovation Solution
A method utilizing a camera and sensor device on a vehicle to record and compare image and sensor data with a digital map, updated in real-time using AI algorithms and multiple sensor systems like radar, LiDAR, and UV/IR cameras, to determine the vehicle's position and create a three-dimensional semantic graph for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If camera-based location methods are used to detect prominent topographical objects, then vehicle position can be determined, but location becomes unreliable when prominent objects are absent or invisible due to weather conditions
Solution Approach 1:
The patent combines multiple sensor types (camera, radar, LiDAR, ultrasonic sensors) to create a hybrid sensing system. Each sensor type compensates for the weaknesses of others - radar provides all-weather capability while camera provides detailed visual recognition, creating reliable location determination under various conditions
Solution Approach 2:
The system employs multiple sensor units that can operate independently or in combination across different weather and lighting conditions. The camera system handles clear conditions while radar and other sensors take over in adverse weather, providing universal location capability
2Ease of operation
If third-party maps are used for vehicle location, then location functions can be implemented, but maps become outdated because updates entail costs or are unavailable
Solution Approach 1:
The system enables vehicles to autonomously update their own maps by capturing sensor data and comparing it with stored reference maps. This self-updating mechanism eliminates dependency on costly third-party updates and ensures maps remain current with the actual environment
Solution Approach 2:
The system continuously compares current sensor data with stored map data, using the discrepancies to identify and update changes in the environment. This feedback loop ensures maps remain synchronized with the actual surroundings without external intervention
3Ease of operation
If GPS position information is used for vehicle locating, then location can be obtained, but GPS information may be erroneous making automated driving assistance functions unreliable
Solution Approach 1:
The system introduces sensor-based map matching as an intermediary between GPS and the automated driving functions. Instead of using GPS directly, the system uses GPS as a rough initial position and refines it through comparison with detailed sensor-captured maps, filtering out GPS errors
4Measurement precision
If multiple sensor systems and AI algorithms are used to enhance location accuracy, then vehicle position determination improves, but system complexity increases
Solution Approach 1:
The system divides the complex sensing and processing task into separate functional modules - data acquisition from multiple sensors, data fusion processing, map creation, and map matching. This modular segmentation manages complexity while maintaining high accuracy through specialized processing in each module
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the reliability and accuracy of vehicle location, enabling safer and more precise autonomous driving by continuously updating and refining the digital map, even in conditions where traditional methods fail.
Implementation Method 1
The camera and sensor device may comprise a radar system
Implementation Method 2
The camera and sensor device may comprise a LiDAR (light detection and ranging) system
Data Source
AI summary
A method for determining a geographical location of a vehicle (10) includes using a camera/sensor device (20) of the vehicle for recording (S10) first image and sensor data (30) from surroundings of the vehicle (10) while the vehicle (10) is traveling a route. The first image and sensor data (30) are assigned geographical coordinates and are sent to a data evaluation unit (50) for creating a digital map. The method continues by using a second camera and sensor device (20) for recording (S40) second image and sensor data (30) from surroundings while the vehicle (10) is traveling the same route and sending (S50) the recorded second image and sensor data (30) to the data evaluation unit (50). The data evaluation unit (50) compares (S60) the recorded second image and sensor data (30) with the digital map of the surroundings (70) and determines (S70) a position of the vehicle (10).