Lane-Level Road Mapping Using Multi-Drive GPS Curve Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating precise lane map data for autonomous vehicles face challenges such as indistinct lane markings, weather obstructions, and the need for highly accurate GPS and 3D mapping, which are costly and require extensive mapping of all road surfaces.
Innovation Solution
An in-vehicle system utilizing a GPS receiver, inertial sensors, and a camera to generate precise lane-level road map data by improving GPS accuracy through curve fitting and correlating data from multiple drives, allowing for cost-effective and dynamic updating of road maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If computer vision is used to detect road or lane boundaries, then lane detection can be performed, but detection reliability deteriorates when lane markings are indistinct, obscured by weather or obstructions, or when lighting conditions are unfavorable
Solution Approach 1:
The patent introduces precision GPS coordinate maps as an intermediary reference system. Instead of relying solely on direct visual detection of lane boundaries, the system uses pre-mapped GPS coordinates of lane centers as a mediator to determine vehicle lane position, bypassing the unreliable visual detection under adverse conditions
Solution Approach 2:
The patent performs preliminary mapping of road lanes to create precision GPS coordinate maps before autonomous driving operation. These pre-established maps contain accurate lane center coordinates that serve as a reference framework, allowing the vehicle to determine lane position without real-time visual detection
2Measurement precision
If precision GPS coordinate maps are created for every road lane to achieve 2 cm to 10 cm accuracy, then positioning precision is improved, but mapping cost and complexity increase significantly
Solution Approach 1:
The patent applies partial mapping by only mapping the centerline of each lane rather than the entire road surface. This selective approach achieves the necessary 2 cm to 10 cm positioning precision while dramatically reducing mapping complexity compared to comprehensive road surface mapping
Solution Approach 2:
The patent focuses mapping efforts on specific critical locations (lane centers) rather than uniformly mapping the entire road. This localized approach concentrates resources on the most important positioning references while avoiding unnecessary mapping of areas that don't contribute to lane position determination
3Measurement precision
If 3D simultaneous localization and mapping is used to correlate vehicle position relative to surrounding features, then positioning can be achieved, but the same precision and complexity problems persist as requiring 100% road surround mapping to 2 cm to 10 cm accuracy
Solution Approach 1:
The patent extracts only the essential positioning information (lane center GPS coordinates) from the complex 3D mapping problem. By taking out just the critical lane centerline data and storing it as simplified 2D GPS coordinate maps, the system achieves precise positioning without the complexity of comprehensive 3D simultaneous localization and mapping
Data Source
AI summary
An in-vehicle system for generating precise, lane-level road map data includes a GPS receiver operative to acquire positional information associated with a track along a road path. An inertial sensor provides time local measurement of acceleration and turn rate along the track, and a camera acquires image data of the road path along the track. A processor is operative to receive the local measurement from the inertial sensor and image data from the camera over time in conjunction with multiple tracks along the road path, and improve the accuracy of the GPS receiver through curve fitting. One or all of the GPS receiver, inertial sensor and camera are disposed in a smartphone. The road map data may be uploaded to a central data repository for post processing when the vehicle passes through a WiFi cloud to generate the precise road map data, which may include data collected from multiple drivers.