Self-Location Mapping with Accuracy-Based Point Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing map creation systems for automatic driving and driving assistance face challenges in achieving high accuracy self-location estimation due to the use of low-accuracy sensors, leading to reduced estimatable sections and decreased accuracy in self-location estimation.
Innovation Solution
A map creation/self-location estimation device that utilizes a combination of sensors with different characteristics to create a map, determines required accuracy based on sensor data, selects and records data accordingly, and estimates the ego vehicle's location using a selection map created during travel.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data from low-accuracy sensors is used for map creation, then the number of estimatable sections increases, but the accuracy of self-location estimation decreases
Solution Approach 1:
The patent applies local quality by determining required accuracy at different predetermined points along the travel route and selecting sensor data accordingly. High-accuracy sensor data is used in sections requiring high precision, while low-accuracy sensor data is used in sections where lower precision is acceptable, thus resolving the contradiction between accuracy and coverage
Solution Approach 2:
The system dynamically adjusts the selection of sensor data based on the specific section being processed. The data selection unit changes which sensor data is used depending on the required accuracy for each predetermined point, making the system adaptive rather than static
2Measurement precision
If data from high-accuracy sensors is used for map creation, then self-location estimation accuracy improves, but the data capacity and storage requirements increase
Solution Approach 1:
The patent extracts only the necessary high-accuracy sensor data for specific predetermined points where high precision is required. Not all sensor data is processed or stored at full accuracy, reducing overall data capacity requirements while maintaining accuracy where needed
Solution Approach 2:
The system changes the accuracy parameter of stored map data based on the required accuracy for each section. Instead of uniformly storing all data at high accuracy, the parameter is adjusted to match local requirements, reducing total data capacity
Data Source
AI summary
An object is to provide a map creation/self-location estimation device capable of estimating a location/attitude of an ego vehicle with high accuracy. The map creation/self-location estimation device includes a map creation unit 110 that creates, from an output of a sensor, a map including a travelling location of an ego vehicle and a point group, a required accuracy determination unit 120 that determines location/attitude estimation accuracy (required accuracy) required for self-location estimation in the next travelling, from the output of the sensor and the map created by the map creation unit 110, a data selection unit 130 that selects a point group included in the map from the map created by the map creation unit 110 and the required accuracy determined by the required accuracy determination unit 120, a map recording unit 140 that records, as a record map, a selection map including the point group selected by the data selection unit 130, the travelling location, and the required accuracy, and a self-location estimation unit 150 that estimates the current location/attitude of a vehicle on the record map by associating the record map recorded in the map recording unit 140 with a current map including the point group selected by the data selection unit 130 and the travelling location of the ego vehicle.