Target-Lane Recognition Using Map Data Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques for recognizing the positional relationship between a target and a lane around a vehicle are inaccurate due to reliance on road curvature estimates and neglect of lane shape changes, leading to suboptimal determination areas and computation inefficiencies.
Innovation Solution
A target-lane relationship recognition apparatus that uses sensor data, map data, and processing to adjust lane geometry based on constraint conditions ensuring the target is within the lane and stationary targets are outside, thereby enhancing accuracy and reducing computation load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If determination area is set based on road curvature at current position, then device complexity is reduced, but measurement precision of lane shape changes deteriorates
Solution Approach 1:
The system pre-acquires high-precision map data containing lane shape information before the vehicle reaches the target area. This preliminary preparation allows the determination area to be accurately defined based on actual lane geometry rather than calculated curvature, resolving the contradiction between simplicity and precision.
Solution Approach 2:
The invention uses map data as a copy or representation of the actual lane geometry. Instead of directly measuring and calculating complex lane shapes in real-time, the system uses pre-stored map data that replicates lane geometry, achieving high measurement precision without increasing device complexity.
2Ease of operation
If conventional determination area method is used, then ease of operation is maintained, but reliability of target-lane relationship recognition deteriorates
Solution Approach 1:
The invention introduces map data as an intermediary element between the vehicle's current position and the determination area definition. This intermediary provides accurate lane shape information that mediates between simple operation and reliable recognition, allowing the system to maintain ease of operation while significantly improving reliability.
3Measurement precision
If lane geometry is adjusted to satisfy constraint conditions, then measurement precision of target-lane relationship improves, but computation load increases
Solution Approach 1:
The system performs lane geometry adjustment in advance by acquiring map data before the vehicle reaches the target area. This preliminary action allows complex computation to be done beforehand, reducing real-time computation load while maintaining high measurement precision during actual operation.
Solution Approach 2:
The invention dynamically adjusts the determination area based on the vehicle's current position and orientation relative to the map data. This dynamic approach allows the system to maintain high precision while optimizing computation by only calculating what is necessary at each moment rather than continuously processing all possible scenarios.
Data Source
AI summary
A target-lane relationship recognition apparatus mounted on a vehicle includes a sensor that detects a situation around the vehicle, a memory device in which a map data indicating a boundary position of a lane on a map is stored, and a processing device. The processing device is configured to: (a) acquire, based on the sensor detection result, target information regarding a moving target and a stationary target around the vehicle; (b) acquire, based on the map data and position-orientation of the vehicle, lane geometry information indicating a lane geometry around the vehicle; (c) adjust the lane geometry to generate an adjusted lane geometry satisfying a condition that the moving target is located within a lane and the stationary target is located outside of any lane; and (d) generate target-lane relationship information indicating a positional relationship between the moving target and the adjusted lane geometry.