Lateral Guidance Using Swarm Data When Camera Detection Fails
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for assisted lateral guidance of motor vehicles face challenges in maintaining availability, especially in situations where lane detection using cameras is inadequate, such as at motorway exits or highway curves.
Innovation Solution
A method utilizing a combination of camera data and swarm data for lateral guidance, where the evaluation and control unit determines lane information from camera data and generates control commands. The method also considers swarm data to support or replace camera data when confidence levels are met, ensuring continuous lateral guidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If lateral guidance is provided exclusively using camera data, then the system structure remains simple, but the availability of lateral guidance deteriorates in situations where lane detection is inadequate (e.g., motorway exits, highway curves)
Solution Approach 1:
The patent combines camera-based lane detection with swarm data from multiple other vehicles to provide lateral guidance. The evaluation and control unit processes both camera data and swarm data, using them in combination to determine lane information. This merging of data sources improves availability in situations where camera data alone is inadequate, while maintaining a unified control structure that manages both inputs.
Solution Approach 2:
The evaluation and control unit is designed to handle multiple functions: it processes camera data for lane detection, processes swarm data from multiple vehicles, validates the plausibility of swarm data, and generates control commands based on the combined information. This multi-functionality allows the system to maintain reliability across diverse driving situations without requiring separate dedicated systems for each function.
2Reliability
If swarm data from multiple vehicles is integrated to support camera data, then the availability of lateral guidance is improved, but the device complexity increases due to additional data processing requirements
Solution Approach 1:
The system implements feedback mechanisms where the evaluation and control unit continuously assesses the plausibility of swarm data by comparing it with camera data and vehicle status information. This feedback loop allows the system to validate whether swarm data should be trusted and used for lateral guidance, improving lane detection accuracy while maintaining control over the complexity through intelligent data validation rather than processing all possible data equally.
Solution Approach 2:
The system changes the parameter of data trustworthiness by introducing confidence levels for swarm data. The evaluation and control unit determines whether swarm data exceeds a predefined confidence level before using it for lateral guidance. This parameter-based approach allows the system to dynamically adjust its reliance on swarm data based on its validated quality, improving accuracy while managing processing complexity through selective data utilization.
3Duration of action of stationary object
If lateral guidance is maintained using swarm data when camera data is unreliable, then the continuity of guidance is improved, but the risk of using potentially inaccurate data increases
Solution Approach 1:
The system performs preliminary validation of swarm data by checking its plausibility against camera data and vehicle status information before using it for lateral guidance. The evaluation and control unit assesses whether swarm data exceeds a predefined confidence level in advance, ensuring that only validated data is used. This preliminary action maintains continuity of guidance while mitigating the risk of using inaccurate data through pre-verification.
Solution Approach 2:
The evaluation and control unit acts as an intermediary between raw swarm data and the lateral guidance system. It validates the plausibility of swarm data by comparing it with camera data and vehicle status, and only transmits validated information to the lateral guidance function. This intermediary role ensures continuity of guidance while filtering out potentially inaccurate data through systematic validation.
Data Source
Figure 1~2
AI summary
The invention relates to a method and a device (1) for at least assisted lateral guidance of a motor vehicle, comprising at least one camera (2), an evaluation and control unit (3) and an actuator (4) for implementing steering interventions, wherein the evaluation and control unit (3) is configured to determine at least one lane from the data (D) of the at least one camera (2) and to generate control commands for the actuator (4) depending on the determined lane, wherein the evaluation and control unit (3) additionally takes swarm data (SD) into account, wherein the evaluation and control unit (3) is further configured such that, in driving situations in which insufficient lane recognition by means of the data (D) of the camera (2) is present or is to be expected, the lateral guidance is carried out by means of the swarm data (SD) if the swarm data (SD) has exceeded a predetermined confidence level.