Vehicle Pose Localization Using Lane Offset and Heading Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current localization techniques for autonomous driving face challenges in achieving centimeter-level accuracy due to geometrical errors in map data and interference in urban environments, leading to inaccurate vehicle positioning, which can result in unsafe navigation.
Innovation Solution
A method that utilizes optimal trajectory estimation and the expectation-maximization framework to search for the best lateral and heading offsets, minimizing errors and providing implicit trajectory smoothing and automated quality assurance, thereby improving localization accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS or similar sensors are used for vehicle localization, then positioning can be provided, but accuracy is insufficient at lane level due to sensor errors and urban environment interference
Solution Approach 1:
The patent introduces map data as an intermediary reference system between the GPS sensor and the vehicle position determination. Instead of relying solely on GPS coordinates, the system uses map matching algorithms that compare GPS readings with pre-stored high-precision map geometries to determine the vehicle's position on the road network, thereby filtering out GPS errors and urban environment interference
Solution Approach 2:
The system implements a feedback mechanism where the estimated vehicle position is continuously compared with expected positions based on map data and vehicle motion models. When discrepancies are detected (such as position jumps or deviations from feasible road segments), the system adjusts the localization estimate by constraining it to valid road geometries, creating a closed-loop correction system that improves both accuracy and reliability
2Measurement precision
If map data with geometrical errors is used for localization, then lane-level positioning can be attempted, but map inaccuracies significantly impact localization precision
Solution Approach 1:
The patent performs preliminary actions by pre-processing and storing high-precision map data including detailed road geometries, lane configurations, and connectivity information before use. This pre-established reference framework allows the localization system to compensate for real-time sensor errors by referencing the预先 prepared accurate map structure, enabling lane-level positioning despite transient measurement uncertainties
Solution Approach 2:
The system segments the localization problem into multiple components: road-level positioning, lane-level positioning, and sub-lane precision positioning. By dividing the continuous space into discrete road segments and lanes with defined geometries, the system can independently optimize positioning accuracy at each level, using map data to constrain and refine position estimates progressively from coarse to fine granularity
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
An approach is provided for localizing a vehicle pose on a map. The approach involves, receiving an input specifying the vehicle pose with respect to a road lane of the map. The approach also involves searching over a set of candidate lateral offsets to select a lateral offset that minimizes a lateral error between the vehicle position with the lateral offset applied and a lateral location of the road lane, wherein the lateral location and the travel direction of the lane are determined from the map. The approach further involves searching over a set of candidate vehicle headings at the selected lateral offset to select a vehicle heading that minimizes a heading error. The approach further involves determining a local optimum of the vehicle pose based on the selected lateral offset and vehicle heading, wherein the vehicle pose is localized to the map based on the local optimum.