Merged Environmental Map for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current environmental map generation methods rely on either vehicle-to-vehicle communication or sensor data, but they lack the integration of both sources effectively, leading to incomplete and unreliable maps.
Innovation Solution
A method for determining a merged environmental map by combining information from vehicle-to-vehicle messages and sensor data, which includes refining the maps based on logical considerations and confidence information, and merging objects and raw data to enhance reliability and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If environmental maps are generated using only vehicle-to-vehicle messages, then communication efficiency is improved, but map reliability and accuracy deteriorate due to incomplete information
Solution Approach 1:
The patent merges two information sources: vehicle-to-vehicle messages and sensor data from the ego vehicle. The message-based environmental map and sensor-based environmental map are combined to create a unified environmental map that leverages the communication efficiency of V2V messages while compensating for their incompleteness using sensor data, thereby improving overall map reliability and accuracy.
2Measurement precision
If environmental maps are generated using only sensor data, then map accuracy is improved, but information completeness deteriorates due to limited sensor coverage
Solution Approach 1:
The patent combines sensor data from the ego vehicle with message-based environmental information from other vehicles and infrastructure. This merging allows the system to maintain high measurement precision through sensor data while improving information completeness by incorporating data from additional sources that extend beyond the ego vehicle's sensor coverage.
3Reliability
If multiple information sources are integrated, then map reliability is improved, but system complexity increases due to multiple data sources
Solution Approach 1:
The patent segments the environmental map generation process into distinct modules: a message-based environmental map determination unit that processes V2V messages, and a sensor-based environmental map determination unit that processes sensor data. These segmented modules operate independently and their outputs are merged, which manages system complexity by organizing multiple information sources into structured, separable processing stages.
Solution Approach 2:
The patent introduces an environmental map merging unit that acts as an intermediary between the message-based map determination and sensor-based map determination. This mediator component integrates the two information sources in a systematic way, managing the complexity of combining multiple data sources while improving map reliability through coordinated fusion of heterogeneous information.
4Speed
If message-based environmental maps are used, then real-time information exchange is improved, but information accuracy deteriorates due to communication limitations
Solution Approach 1:
The patent employs feedback mechanisms where the sensor-based environmental map serves as a reference to validate and correct message-based environmental information. The system continuously compares message-based data with sensor-based data, using the more accurate sensor measurements to correct inaccuracies in the message-based map, thereby maintaining real-time information exchange while improving overall information accuracy.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Embodiments relate to a vehicle, an apparatus, a method, and a computer program for determining a merged environmental map of the vehicle. The method (10) for a vehicle (100) and for determining a merged environmental map of the vehicle (100) comprises obtaining (12) information related to a first environmental map, which is based on messages communicated with other vehicles or infrastructure in the environment. The method (10) comprises obtaining (14) information related to a second environmental map, which is based on sensor data of the vehicle (100). The method (10) further comprises determining (16) the merged environmental map based on the information related to the first environmental map and the information related to the second environmental map.