Autonomous Vehicle Map Generation Using Onboard Detector Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for generating maps for autonomous vehicles are inefficient due to the need for separate equipment, long processing times, and low accuracy in position detection, particularly in reflecting detector characteristics of autonomous vehicles.
Innovation Solution
A vehicle system equipped with a detector to gather driving environment information, a controller to generate and update maps by extracting effective data, clustering, and using quadratic or cubic equations to define lanes and trajectories, and a storage system to compare and update maps based on detected changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If separate equipment is used for map production, then map generation can be performed, but device complexity increases and additional equipment is required
Solution Approach 1:
The vehicle detector is designed to serve dual purposes: it detects driving environment information for autonomous navigation and simultaneously collects data for map generation. This eliminates the need for separate map production equipment by making the existing detector multi-functional.
Solution Approach 2:
The autonomous vehicle performs map generation using its own detector and controller without requiring external specialized equipment. The vehicle serves itself by utilizing its existing sensing capabilities to create and update maps, thereby reducing overall system complexity.
2Manufacturing precision
If traditional map generation methods are used, then maps can be created, but processing time is long
Solution Approach 1:
The system continuously collects driving environment information during normal vehicle operation and continuously updates the map in real-time. This eliminates the need for separate, time-consuming map production processes by making map generation an ongoing activity that occurs during regular driving.
Solution Approach 2:
The vehicle pre-collects driving environment information during normal operation and uses this data to proactively update maps before they are needed. The controller continuously processes detector data to maintain up-to-date maps, so when map data is required, it is already available without additional processing time.
3Productivity
If general detector data is used for map generation, then map can be created, but position detection accuracy is low
Solution Approach 1:
The controller selectively processes detector data based on local characteristics of the driving environment. It identifies and processes only the relevant portions of detector data that correspond to specific map features, applying appropriate processing methods to each local area to maximize position detection accuracy.
Solution Approach 2:
The system changes processing parameters based on the type of detector data being analyzed. Different clustering algorithms and processing methods are applied depending on whether the data represents terrain features, lanes, or other map elements, thereby optimizing position detection accuracy for each specific case.
Data Source
AI summary
A vehicle, a control method thereof, and an autonomous driving system using the same, may include a vehicle detector configured to detected driving environment information about surroundings of a vehicle, and a controller configured to generate a map including at least one of a surrounding terrain, a lane, and a traveling route based on the detected driving environment information.