Vehicle Obstacle Control Using Type-Specific Detection Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated driving technologies face challenges in reliably detecting obstacles due to environmental changes and lack of differentiation between obstacle types, leading to unnecessary activation of collision avoidance systems and unnatural vehicle behavior.
Innovation Solution
A vehicle control device that utilizes in-vehicle and roadside sensors, combined with map information and vehicle position data, to generate obstacle information and evaluate the presence and type of obstacles, determining appropriate responsive control based on obstacle-presence possibility lists.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If obstacle detection is performed using sensor information without evaluating obstacle type, then detection coverage is improved, but detection reliability deteriorates due to false positives from environmental changes
Solution Approach 1:
The patent segments the detection process by dividing obstacles into different type categories (vehicle, motorcycle, bicycle, human, other). Each obstacle type has its own evaluation criteria and provability value thresholds, allowing the system to assess detected objects more accurately according to their specific characteristics rather than using a single unified detection mechanism.
Solution Approach 2:
The patent performs preliminary classification of detected obstacles into type categories before final verification. By pre-defining obstacle types and their corresponding evaluation criteria in advance, the system can quickly filter and evaluate detected objects using appropriate standards, reducing false positives from environmental changes while maintaining detection coverage.
2Measurement precision
If obstacle detection is performed without considering environmental changes, then response speed is improved, but detection accuracy deteriorates due to weather and road conditions
Solution Approach 1:
The patent applies different evaluation criteria and provability value thresholds to different obstacle types based on their local characteristics. For example, vehicles have different detection criteria than pedestrians or cyclists. This localized approach allows the system to maintain high detection accuracy for each obstacle type while processing them efficiently according to their specific properties rather than applying a uniform evaluation process.
3Reliability
If AEB function is activated for all detected obstacles, then safety is improved, but ride comfort deteriorates due to unnecessary activation
Solution Approach 1:
The patent changes the determination parameter from a single unified criterion to multiple type-specific provability value thresholds. Each obstacle type has its own threshold for triggering AEB function. This allows the system to maintain high safety standards by accurately assessing real obstacles while avoiding unnecessary AEB activation for false positives, thereby preserving ride comfort and operational naturalness.
Data Source
AI summary
A vehicle control device includes: an in-vehicle sensor information acquisition unit; a roadside sensor information acquisition unit; a vehicle position information acquisition unit; a map information acquisition unit; an obstacle information generation unit that generates obstacle information including information of at least one of a position, a size and a speed of the obstacle and information of a type of the obstacle, on the basis of the in-vehicle sensor information, the roadside sensor information and the vehicle position information; and an obstacle responsive control unit that determines whether or not to execute obstacle responsive control, on the basis of the obstacle information and an obstacle-presence possibility list for respective types of obstacles, and then, when determined to execute the obstacle responsive control, controls the vehicle in response to the obstacle.