Vehicle Localization Using Dynamic Landmarks in Landmark-Poor Roads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle positioning systems, such as GNSS and landmark-based methods, face challenges in accuracy and reliability, especially in areas with poor satellite coverage and insufficient landmarks, leading to positioning errors and failures in scenarios like tunnels or rural roads.
Innovation Solution
A method that utilizes surrounding vehicles as dynamic landmarks to determine the map position of an ego-vehicle by measuring their position and velocity relative to the ego-vehicle, transforming these measurements into a global coordinate system, and combining them with stationary landmarks for enhanced accuracy and robustness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If landmark-based positioning is used, then positioning accuracy is improved in areas with sufficient landmarks, but reliability deteriorates in areas with insufficient landmarks (e.g., rural roads, tunnels)
Solution Approach 1:
The patent applies the dynamics principle by transforming static landmarks into dynamic landmarks. Instead of relying on fixed landmarks that may be absent in certain areas, the system uses moving vehicles as temporary reference points. These dynamic landmarks are tracked and predicted to maintain positioning accuracy in environments where traditional static landmarks are insufficient, thereby improving both accuracy and reliability simultaneously.
2Reliability
If GNSS and IMU are used for positioning, then positioning capability is maintained in various conditions, but accuracy deteriorates due to large scale and bias errors
Solution Approach 1:
The patent applies the intermediary principle by introducing dynamic landmarks (surrounding vehicles) as mediator reference points between the ego-vehicle and the positioning system. These intermediaries provide additional geometric constraints that help correct the scale and bias errors inherent in GNSS-IMU positioning, thereby improving accuracy while maintaining the reliability of continuous positioning capability.
3Measurement precision
If forward-looking sensors are used to perceive road geometry, then direct perception capability is improved, but reliability deteriorates in scenarios with overlapping roads or closely located road segments
Solution Approach 1:
The patent applies the feedback principle by continuously tracking the positions of dynamic landmarks and using this information to correct and refine the ego-vehicle's position estimation. The system feeds back the relative positions and movements of surrounding vehicles to disambiguate overlapping road geometries, thereby maintaining reliable positioning even when forward-looking sensors cannot clearly distinguish between closely located road segments.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure relates to a method (100, 200), system (10) and computer program product for determining a map position of an ego-vehicle (1). The method includes acquiring (101) map data comprising a road geometry, initializing (102) at least one dynamic landmark by measuring a position and velocity, relative to the ego-vehicle, of a surrounding vehicle (2a, 2b, 2c), and determining (105) 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 (106) of the surrounding vehicle, and measuring (107) 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.