Vehicle Localization Using Dynamic Landmarks Without GNSS
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle positioning systems, such as GNSS and landmark-based methods, face challenges in accuracy and reliability, especially in areas with poor satellite coverage or insufficient stationary landmarks, leading to positioning errors and failures in autonomous driving scenarios.
Innovation Solution
A method that utilizes surrounding vehicles as dynamic landmarks by measuring their position and velocity relative to the ego-vehicle, predicting their future positions based on road geometry, and updating the ego-vehicle's geographical position, combining this with stationary landmark data for enhanced accuracy and robustness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If GNSS and IMU are used for positioning, then positioning coverage is improved, but positioning accuracy deteriorates due to large scale and bias errors
Solution Approach 1:
The patent introduces map data and landmark information as intermediary references to correct GNSS/IMU positioning errors. By comparing sensor-derived position with map-based expected position and using landmarks as verification points, the system mediates between the coarse GNSS/IMU positioning and the required high accuracy, achieving correction of scale and bias errors without relying solely on satellite signals.
2Measurement precision
If landmark based positioning is used, then positioning accuracy is improved, but reliability deteriorates when landmarks are insufficient or undetected
Solution Approach 1:
The patent creates a multi-functional positioning system that can operate using multiple different reference sources: GNSS satellites, map data, stationary landmarks, and dynamic landmarks (surrounding vehicles). The system automatically selects and switches between these different positioning methods based on availability and reliability, ensuring continuous accurate positioning whether landmarks are present or absent, thus achieving universal positioning capability across all driving scenarios.
3Reliability
If multiple sensors are combined for positioning, then positioning reliability is improved, but system complexity increases
Solution Approach 1:
The patent implements a dynamic positioning system that adaptively selects and weights different positioning sources based on real-time conditions. The system dynamically adjusts which sensors and reference data are active, their relative weights in the fusion algorithm, and switches between positioning methods as conditions change (e.g., tunnel entry, landmark occlusion). This dynamic adaptation achieves high reliability without requiring all sensors to operate at full complexity simultaneously, reducing overall system burden.
4Measurement precision
If stationary landmarks are used for positioning, then positioning accuracy is improved in areas with landmarks, but adaptability deteriorates in areas without landmarks
Solution Approach 1:
The patent segments the positioning reference system into two distinct components: stationary landmarks (for high accuracy when available) and dynamic landmarks (surrounding vehicles, for coverage when stationary landmarks are absent). This segmentation allows the system to use stationary landmarks for precise positioning in urban areas with rich landmark coverage, while seamlessly transitioning to dynamic landmark-based positioning in rural areas or tunnels where stationary landmarks are unavailable, achieving both accuracy and adaptability.
Data Source
AI summary
A method, system and computer program product for determining a map position of an ego-vehicle are disclosed. The method includes acquiring map data comprising a road geometry, initializing at least one dynamic landmark by measuring a position and velocity, relative to the ego-vehicle, of a surrounding vehicle, and determining a first map position of the surrounding vehicle based on this measurement and the geographical position of the ego-vehicle. Further, the method includes predicting a second map position of the surrounding vehicle, and measuring a location, relative to the ego-vehicle, of the surrounding vehicle when it is estimated to be at the second map position, whereby the geographical position of the ego-vehicle can be computed and updated.