Vehicle Surroundings Analysis via Multi-Sensor Majority Voting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for analyzing the surroundings of a motor vehicle are not efficient in providing reliable results, as they often rely on single sensor data without redundancy or diversity, leading to potential errors in object detection.
Innovation Solution
A method that analyzes the surroundings multiple times using diverse sensors and analysis methods, determining overall results based on a majority of individual results, ensuring robustness and reliability by compensating for errors through redundancy and diversity in sensor data acquisition and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If single sensor data is used for surroundings analysis, then device complexity is reduced, but reliability of object detection deteriorates due to lack of redundancy
Solution Approach 1:
The patent applies local quality by using heterogeneous sensor types (camera, radar, LIDAR, ultrasound) with different detection characteristics for different aspects of surroundings monitoring. Each sensor type has specific local strengths (e.g., camera for visual recognition, radar for distance measurement) that complement each other, improving overall detection reliability while managing system complexity through specialized rather than universal sensing.
Solution Approach 2:
The patent implements composite materials principle by fusing data from multiple diverse sensor types to create a composite perception system. The evaluation unit combines information from camera, radar, LIDAR, and ultrasound sensors to form a unified and more reliable object detection result, similar to how composite materials combine different materials to achieve superior properties.
2Reliability
If multiple sensors and analysis methods are used, then reliability of analysis results is improved, but device complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the surroundings analysis into multiple independent analysis units, each responsible for evaluating data from specific sensor types or detection aspects. The evaluation unit processes inputs from multiple sensors separately before fusing results, which modularizes the complex analysis system and makes it more manageable while maintaining high reliability through diversified analysis paths.
Solution Approach 2:
The patent implements feedback mechanisms where the evaluation unit continuously receives data from multiple sensors, compares results, and adjusts object detection outcomes based on consensus or discrepancy analysis. This feedback loop ensures that unreliable detections from individual sensors can be corrected by other sensors, improving overall trustworthiness while using structured feedback processes to manage complexity.
3Reliability
If majority voting method is used for determining overall result, then reliability of final detection is improved, but processing time increases
Solution Approach 1:
The patent applies periodic action by organizing multiple sensor analyses to operate in synchronized cycles or periods. Instead of sequentially processing all sensors one after another, the system performs periodic analysis rounds where multiple sensors capture and evaluate data in parallel time windows, then combines results through majority voting. This reduces total processing time while maintaining the reliability benefits of multiple analyses.
Solution Approach 2:
The patent merges multiple parallel analysis results into a single unified detection outcome through the evaluation unit. By combining the outputs of multiple sensors and analysis methods simultaneously and applying majority voting or fusion algorithms, the system achieves robust object detection without requiring sequential processing, thus minimizing time loss while maximizing reliability.
Data Source
AI summary
A method for analyzing the surroundings of a motor vehicle. The surroundings are analyzed multiple times in order to determine multiple results in each case. Each of the multiple results indicates at least whether an object is located in the surroundings of the motor vehicle or not. It is determined, as an overall result, that an object is located in the surroundings of the motor vehicle if a majority of the multiple results indicates that an object is located in the surroundings of the motor vehicle. It is determined, as an overall result, that no object is located in the surroundings of the motor vehicle if a majority of the multiple results indicates that there is no object in the surroundings of the motor vehicle. A device, a system, a computer program, and a machine-readable storage medium are also described.