Electronic Control Device for Sensor Fusion and Behavior Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic drive systems face complexity and increased arithmetic load due to the need for multiplexing sensors and calculations to detect abnormalities, which complicates continuous operation and safe transition from automatic to manual control during failures.
Innovation Solution
An electronic control device incorporating a sensor fusion processing unit to integrate sensor information, a behavior prediction processing unit to predict future object behavior, and comparison units to verify predictions against sensor outputs, allowing for abnormality detection without additional sensors or complex multiplexing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiplexing of sensors and calculations is performed to detect abnormalities, then abnormality detection capability is improved, but device complexity and arithmetic load increase
Solution Approach 1:
The patent segments the abnormality detection function into two distinct modules: a sensor fusion processing unit that integrates sensor information, and a behavior prediction processing unit that predicts future object behavior. This segmentation allows each unit to have a specialized, simplified function rather than requiring complex multiplexed sensor arrangements, thereby maintaining abnormality detection capability while reducing system complexity.
Solution Approach 2:
The behavior prediction processing unit performs preliminary action by predicting future behavior of target objects before actual abnormalities occur. By comparing predicted future sensor outputs with actual sensor outputs, the system can detect abnormalities in advance. This preliminary prediction approach eliminates the need for complex real-time multiplexing of multiple sensors during abnormality detection.
2Reliability
If multiplexing of sensors and calculations is performed to detect abnormalities, then abnormality detection capability is improved, but arithmetic load increases
Solution Approach 1:
The patent divides the processing load into two separate units: sensor fusion processing that integrates sensor data, and behavior prediction processing that calculates future states. This segmentation distributes the arithmetic load efficiently, avoiding the need for complex multiplexed calculations that would otherwise be required to achieve the same abnormality detection capability.
Solution Approach 2:
By performing behavior prediction in advance and storing the results, the system reduces the arithmetic load during real-time operation. The comparison unit simply needs to compare predicted values with actual sensor readings, rather than performing complex multiplexed calculations in real-time, thereby maintaining abnormality detection capability while reducing overall arithmetic load.
3Reliability
If verification methods using additional sensors are implemented, then sensor abnormality detection is improved, but device complexity increases
Solution Approach 1:
The patent segments the verification function into a dedicated behavior prediction processing unit that uses sensor fusion results to predict future behavior. This segmentation allows verification to be performed using existing sensor data processed through fusion, rather than requiring additional verification sensors, thereby maintaining sensor verification capability while reducing system complexity.
Solution Approach 2:
The sensor fusion processing unit acts as an intermediary that integrates sensor information and provides a unified data source for both control and verification purposes. The behavior prediction unit then uses this fused data to generate predicted outputs for comparison, eliminating the need for additional verification sensors and reducing system complexity while maintaining verification capability.
Data Source
AI summary
An electronic control device including a sensor fusion processing unit that integrates a plurality of pieces of sensor information having been input from a plurality of sensors. The electronic control device further including a behavior prediction processing unit that obtains a future value in which a future behavior of a target object is predicted based on joint information integrated by the sensor fusion processing unit. The electronic control device further including a comparison unit that compares a future value predicted by the behavior prediction processing unit with output information of each sensor of the sensor fusion processing unit at a predicted time.