Vehicle Control Device Sensor Fusion Position Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control devices face significant errors in calculating the position of objects due to the relationship between distance and orientation when using both electromagnetic wave sensors and image sensors, which can lead to unwanted operations in collision avoidance systems.
Innovation Solution
A vehicle control device and method that acquires and processes information from both electromagnetic wave sensors and image sensors to determine the position of a target object, adjusting the calculation based on the reliability of the identicalness determination between the two sensor types, using either the first distance and orientation or the second distance and orientation depending on the reliability level, to minimize errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the position of a target object is calculated using a distance to an object detected with an electromagnetic wave sensor and an orientation of an object detected with an image sensor, then the position can be determined using multi-sensor data, but a significant error in the calculated position may occur depending on the relationship between the distance and orientation
Solution Approach 1:
The system dynamically changes the parameters used for position calculation based on the reliability of identicalness determination. When reliability is high, it uses the electromagnetic wave sensor distance and image sensor orientation; when reliability is low, it switches to using only image sensor data. This parameter switching resolves the contradiction by adapting the calculation method to the current reliability condition.
Solution Approach 2:
The position calculation system transitions from a static approach (always using the same sensor combination) to a dynamic approach where the calculation method changes based on real-time reliability assessment. The system dynamically selects between two calculation modes: using electromagnetic wave sensor data when reliable, and using only image sensor data when unreliable, thereby maintaining measurement precision across varying conditions.
2Loss of information
If the vehicle control device uses both electromagnetic wave sensor and image sensor data to calculate object position, then more information is available for calculation, but errors are likely to occur in the calculation of the distance to an object detected using the image sensor
Solution Approach 1:
The reliability determination unit acts as an intermediary that assesses the quality of sensor data before it is used for position calculation. It evaluates whether the identicalness determination between electromagnetic wave sensor and image sensor detections is reliable, and based on this assessment, decides whether to use the electromagnetic wave sensor distance data or switch to image sensor distance data, thereby preventing error propagation.
Solution Approach 2:
The system implements a feedback mechanism where the reliability of identicalness determination is continuously evaluated and used to adjust the position calculation method. When the feedback indicates low reliability, the system switches to using only image sensor data, avoiding the propagation of errors from unreliable electromagnetic wave sensor measurements.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach effectively reduces positional errors in target object calculations, ensuring accurate collision avoidance by prioritizing the second distance and orientation when reliability is low and using the first distance and orientation when reliability is high, thereby improving the precision of object positioning.
Implementation Method 1
acquires, using an electromagnetic wave sensor, a first distance and a first orientation of a first object with respect to a host vehicle
Implementation Method 2
acquires, using an image sensor, a second distance and a second orientation of a second object with respect to the host vehicle
Data Source
AI summary
An ECU determines that detected first and second objects are identical as an identical object based on a first position of the first object and a second position of the second object, and calculates the position of a target object that is determined as the identical object. The ECU determines whether a current situation is such that a reliability of the identicalness determination is at a predetermined level or higher. In a case of determining the current situation to be such that the reliability is at the predetermined level or higher, the ECU calculates the position of the target object based on a first distance and a second orientation. In a case of determining the current situation not to be such that the reliability is at the predetermined level or higher, the ECU calculates the position of the target object based on a second distance and the second orientation.