Vehicle Location Recognition Using Landmark Vision and Range Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high cost of expensive equipment like GPS/RTK systems makes it difficult to commercialize unmanned autonomous driving services, as they are necessary for determining a vehicle's location and heading for control and obstacle management.
Innovation Solution
An apparatus and method using an image camera and range sensor to recognize landmarks around a road, calculating the vehicle's location and heading based on image and distance information, eliminating the need for expensive GPS/RTK systems by employing a landmark recognition unit, distance recognition unit, and vehicle location calculation unit.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS/RTK systems are used to obtain vehicle location and heading information, then measurement precision is improved, but device cost increases
Solution Approach 1:
The patent uses image cameras to capture visual images of landmarks and creates a digital representation of the landmark environment. Instead of directly using expensive GPS/RTK hardware, the system copies the navigation function by processing visual information to determine vehicle location and heading, replacing physical positioning equipment with optical sensing and computational methods.
Solution Approach 2:
The patent replaces the mechanical/electronic GPS/RTK positioning system with an optical-based vision system. Image cameras capture landmark images, and computer vision algorithms process these images to extract location and heading information, substituting a mechanical positioning system with an optical-information processing system that is more cost-effective.
2Reliability
If expensive GPS/RTK equipment is required for autonomous driving, then reliability of location information is improved, but ease of manufacture worsens
Solution Approach 1:
The patent replaces expensive, high-precision GPS/RTK equipment with cheaper image cameras and range sensors. While individual sensor components are less expensive, the system achieves comparable reliability through algorithmic processing of multiple sensor inputs, making autonomous driving systems more affordable and easier to manufacture for commercial deployment.
Solution Approach 2:
The patent makes the image camera and range sensor perform multiple functions: they not only capture environmental information for navigation but also detect obstacles, recognize landmarks, and provide spatial awareness. This multi-functionality reduces the need for specialized expensive equipment while maintaining reliability across multiple operational requirements.
Data Source
AI summary
Disclosed herein are an apparatus and method for recognizing the location of a vehicle. The apparatus includes a landmark recognition unit, a distance recognition unit, and a vehicle location calculation unit. The landmark recognition unit receives information about images of landmarks, indicated around a road in a direction in which the vehicle is traveling, from an image sensor, and recognizes a reference landmark closest to the vehicle based on the image information. The distance recognition unit collects values of distances to the reference landmark from the range sensor. The vehicle location calculation unit calculates the final location of the vehicle based on basic information about the reference landmark and the distance values.