Vehicle Localization Using Artificial Road Markings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle localization methods, particularly in urban and safety-relevant areas, face limitations due to the partial usability of GPS sensors and high computing requirements for camera-based systems, leading to insufficient precision for automated driving tasks.
Innovation Solution
A method utilizing artificial markings detectable by multiple sensors, such as radar, video, and LIDAR, which are integrated into a digital map to enable precise vehicle localization by calculating distances and directions, providing a redundant and robust positioning system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS sensors are used for vehicle localization, then the system is simple to operate, but the positioning precision is insufficient in urban and safety-relevant areas
Solution Approach 1:
The patent introduces artificial markings as intermediary objects between the vehicle sensors and the GPS satellite system. These markings serve as additional reference points that mediate the localization process, allowing vehicles to achieve higher precision positioning in urban canyons and safety-relevant areas where GPS signals are weak or blocked. The markings are integrated into the digital map and detected by vehicle sensors to provide supplementary positioning information.
Solution Approach 2:
The artificial markings serve multiple functions: they act as reference points for precise localization, provide redundancy for GPS failures, enable vehicle-to-infrastructure communication, and support multiple sensor types (camera, radar, LIDAR). This multi-functionality allows a single infrastructure element to address various localization challenges simultaneously.
2Measurement precision
If camera-based algorithms are used to extract location features, then the positioning precision can be improved, but the computing effort increases significantly
Solution Approach 1:
Instead of using complex algorithms to extract and recognize natural urban features from camera images, the system uses pre-defined artificial markings with simple, recognizable geometric patterns. These markings are copied from the digital map to the physical infrastructure, creating standardized reference objects that can be identified through simple pattern matching rather than complex feature extraction, thereby reducing computing effort while maintaining high positioning precision.
Solution Approach 2:
The patent changes the parameters of the reference objects from natural, variable urban features to standardized artificial markings with controlled geometric parameters. This transformation allows the use of simpler detection algorithms with lower computational requirements, as the markings have fixed shapes, sizes, and patterns that can be recognized through efficient template matching rather than complex scene understanding.
3Reliability
If artificial markings are introduced for precise localization, then the positioning precision and reliability are improved, but the infrastructure complexity increases
Solution Approach 1:
The localization infrastructure is segmented into modular artificial markings that can be independently installed, maintained, and replaced. Each marking is a discrete unit with standardized dimensions and patterns, allowing the system to achieve high reliability through distributed redundancy rather than through complex integrated systems. The segmentation enables flexible deployment strategies where markings can be added incrementally in safety-relevant areas.
4Measurement precision
If multiple sensors are used to detect markings, then the robustness and precision of localization are improved, but the device complexity and cost increase
Solution Approach 1:
The artificial markings are designed to be universally detectable by multiple sensor types (camera, radar, LIDAR) using the same physical object. This multi-functionality allows vehicles equipped with different sensor suites to achieve high-precision localization without requiring vehicle-specific infrastructure, thereby reducing overall system complexity while maintaining high measurement precision through sensor fusion.
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 ensures high precision and reliability in vehicle localization, achieving positioning accuracy of ±10 cm in safety-relevant areas, enhancing the reliability of automated driving systems and supporting GNSS-based positioning.
Implementation Method 1
The marking is simultaneously detectable by at least two different sensors of vehicles
Implementation Method 2
A method utilizing artificial markings detectable by multiple sensors, such as radar, video, and LIDAR
Data Source
AI summary
A method, which can be implemented by a control unit, for carrying out a localization of at least one vehicle by a vehicle-side control unit includes receiving measuring data from at least one sensor, ascertaining at least one marking from the measuring data, and associating the ascertained marking with a marking entered into a digital map for determining a position.