3D Vehicle Map Generation for Real-Time Precision Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional maps used for vehicle navigation are often low in precision, lack details, and become outdated quickly, especially when signal availability is limited.
Innovation Solution
A system and method for generating a high-precision map using data collected by sensors on-board vehicles, which can be updated in real-time and shared among vehicles, utilizing cloud computing for processing and transmission to create a three-dimensional map for accurate navigation and obstacle avoidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional maps are used for vehicle navigation, then the navigation system is simple to implement, but the map precision and detail are low and become outdated quickly
Solution Approach 1:
The patent combines sensor data from multiple vehicles with cloud computing resources to generate high-precision maps. By merging data from various sources (LiDAR, cameras, GPS) and processing capabilities, the system achieves superior map precision without relying on a single complex component.
Solution Approach 2:
The generated high-precision maps serve multiple functions: navigation guidance, obstacle detection, route planning, and real-time vehicle positioning. This multi-functionality allows the map to replace several separate systems, maintaining simplicity while improving precision.
2Reliability
If high-precision maps are generated using multiple vehicle sensors and cloud processing, then map precision and real-time updates are improved, but data transmission and processing complexity increase
Solution Approach 1:
The cloud server acts as an intermediary that receives raw sensor data from multiple vehicles, processes it using advanced algorithms, and returns refined map information. This mediator approach allows complex processing to occur centrally while keeping individual vehicle systems relatively simple.
Solution Approach 2:
The system performs preliminary data processing and filtering at the vehicle level before transmission, and conducts comprehensive processing at the cloud level. This staged approach ensures reliable map generation while managing complexity through progressive refinement.
3Speed
If sensor data is collected and processed on-board the vehicle, then real-time navigation is achieved, but computational load and energy consumption increase
Solution Approach 1:
The processing task is segmented between vehicle-based pre-processing (filtering, feature extraction) and cloud-based post-processing (integration, refinement). This division allows real-time responsiveness at the vehicle level while distributing the heavier computational energy cost to the cloud infrastructure.
Solution Approach 2:
The vehicle performs partial processing locally to achieve real-time navigation needs, transmitting only essential data to the cloud. This partial action approach ensures speed for immediate navigation while avoiding excessive energy consumption from complete on-board processing.
4Measurement precision
If map data is shared among multiple vehicles through high-speed networks, then navigation accuracy for all vehicles improves, but network bandwidth and transmission requirements increase
Solution Approach 1:
The system extracts and transmits only the essential and changed map features to the cloud and among vehicles, rather than transmitting complete raw datasets. This extraction approach maintains navigation accuracy while significantly reducing the quantity of data that needs to be transmitted over the network.
Data Source
AI summary
A method of map generation includes receiving data from a plurality of vehicles about environments within which the plurality of vehicles operate, and generating a three-dimensional map using the data from the plurality of vehicles. The data is collected by one or more sensors on-board the plurality of vehicles.