Autonomous Vehicle Position Correction via Collaborative Cognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurate object recognition and position estimation due to distance-dependent cognitive accuracy issues with sensors, and unreliable information sharing with other vehicles, which affects driving safety and reliability.
Innovation Solution
A method for precise position correction in autonomous vehicles using collaborative cognition, involving sensor data estimation, shared message reception from connected vehicles and infrastructure devices, error calculation, and radius setting for correcting object information through interpolation and error application.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If sensor data is used for object recognition, then detection capability is improved, but measurement precision deteriorates with increasing distance
Solution Approach 1:
The patent combines sensor data from the autonomous vehicle with shared message data from other vehicles and infrastructure devices to create a fused object information record. This merging allows the system to maintain detection capability across large distances by compensating for individual sensor limitations through collaborative data aggregation.
Solution Approach 2:
The system calculates estimated errors by comparing sensor-estimated object information with shared message information, then uses this feedback to correct position estimates. This closed-loop feedback mechanism continuously improves measurement precision by identifying and correcting discrepancies between different data sources.
2Reliability
If collaborative cognition with multiple vehicles is implemented, then information reliability is improved, but device complexity increases
Solution Approach 1:
The patent segments the collaborative cognition system into distinct functional modules: a receiving module for acquiring shared messages, a calculation module for computing estimated errors, and a correction module for applying position corrections. This segmentation manages system complexity by organizing complex interactions into manageable, independent components.
Solution Approach 2:
The system introduces a standardized shared message format as an intermediary that enables reliable information exchange between diverse vehicles and infrastructure devices. This intermediary layer simplifies complexity by providing a common communication protocol that abstracts away the heterogeneity of different data sources.
3Measurement precision
If position correction is applied to all detected objects, then measurement precision is improved, but loss of time increases due to processing overhead
Solution Approach 1:
The patent applies position correction selectively based on local conditions: it calculates estimated errors and applies corrections primarily to objects where discrepancies between sensor data and shared message data exceed a threshold. This local quality approach improves precision for critical cases without uniformly processing all objects, thereby reducing overall processing time.
Solution Approach 2:
The system performs partial correction by applying error correction only to specific objects or parameters that require it, rather than correcting all object attributes universally. This partial action strategy maintains measurement precision for critical position estimates while minimizing unnecessary processing overhead.
Data Source
AI summary
A precise position correction method based on collaborative cognition in an autonomous vehicle includes: estimating object information on a road within a detection range on an autonomous vehicle; receiving a shared message from at least one of a first vehicle (another connected vehicle (CV) or automated vehicle (CAV)) and a road infrastructure device for V2X communication on the road, receiving the message including driving status information of the other CV when the first vehicle is the other CV, and receiving the driving status information of the other CAV and the message about a second vehicle, in which the V2X communication is not possible, recognized by the other CAV; calculating an estimated error by comparing the estimated object information with the message; and setting a radius based on the first vehicle corresponding to an estimated error application radius in consideration of a distance between the autonomous vehicle and the first vehicle.