Vehicle Running Support Control Logic for Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle running support systems that combine radar and image recognition for obstacle detection lack appropriate control methods when only one of the detecting means detects an obstacle, leading to potential inaccuracies and inefficiencies in support control.
Innovation Solution
A running support system that adjusts control conditions based on the results of detection by both radar and image recognition means, shifting starting conditions for support control depending on whether both or only one of the systems detect an obstacle, and considering the driver's inattentive condition to optimize support interventions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If two or more types of obstacle detecting means are provided, then detection coverage is improved, but detection reliability deteriorates when only part of the means detect an obstacle
Solution Approach 1:
The control conditions are dynamically adjusted based on the combination of detection results from radar and image recognition means. When both means detect an obstacle, more aggressive control is applied; when only one detects, more conservative control is used. This dynamic adaptation resolves the contradiction by making the system reliable without requiring all detecting means to agree.
Solution Approach 2:
The patent changes control parameters (control start time, threshold values) based on which detecting means identified the obstacle. Radar-detected obstacles trigger earlier control activation, while image-recognition-only obstacles trigger later activation. This parameter adjustment allows the system to handle multiple detecting means reliably without increasing overall complexity.
2Speed
If control start time is advanced to improve response, then response time is improved, but false alarms increase
Solution Approach 1:
Different control start times and threshold values are applied locally based on which detecting means identified the obstacle. Radar-detected obstacles receive earlier control activation with lower thresholds, while image-recognition-only obstacles receive later activation with higher thresholds. This local differentiation allows fast response when necessary while reducing false alarms when uncertain.
Solution Approach 2:
The patent uses an intermediate evaluation layer that assesses the reliability of each detecting means before triggering control. The radar serves as a high-reliability intermediary that can trigger early control, while image recognition serves as a lower-reliability intermediary that triggers control only under more certain conditions. This intermediary evaluation resolves the contradiction between speed and accuracy.
3Measurement precision
If image recognition means is used to improve obstacle identification, then identification accuracy is improved, but detection reliability deteriorates due to erroneous detection
Solution Approach 1:
The patent applies partial control action when only image recognition detects an obstacle, using later control start times and higher threshold values compared to radar detection. This partial action approach allows the system to utilize image recognition's identification capabilities while compensating for its lower reliability through more conservative control parameters.
Solution Approach 2:
The control system dynamically adjusts its response based on which detecting means identified the obstacle. When image recognition identifies an obstacle without radar confirmation, the system applies more conservative control conditions. When both means agree, the system applies more aggressive control. This dynamic adjustment resolves the contradiction by adapting control intensity to the reliability of the identification source.
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
Enhances the reliability and accuracy of support control by adjusting the timing and intensity of interventions based on the combination of detection results, reducing false alarms and improving the driver's ability to respond to obstacles, while minimizing unnecessary interventions.
Implementation Method 1
first object detecting means for detecting an object near a vehicle using a radar
Implementation Method 2
second object detecting means for detecting an object near the vehicle by performing image recognition based on an obtained image of an area near the vehicle
Data Source
AI summary
There is provided a running support system for a vehicle, which supports running of a vehicle by using a radar and image recognition means as obstacle detecting means, and in which appropriate support control based on a result of detection performed by each control means is set. A result of obstacle detection performed by a millimeter wave radar (21) is checked against a result of obstacle detection performed by image recognition means (22). Then, a starting condition for the running support control is changed depending on whether an obstacle has been detected by both the millimeter wave radar (21) and the image recognition means (22), or an obstacle has been detected by only one of the millimeter wave radar (21) and the image recognition means (22). Thus, the control support is performed based on an inattentive condition of a driver.