AEB Brake Pre-Fill Control for Road Gradient Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advanced driver assistance systems (ADAS) face performance degradation in identifying front obstacles and responding to collision risks due to changes in road gradient, particularly affecting autonomous emergency braking (AEB) functions.
Innovation Solution
A system that utilizes a camera and processor to identify lane lines and road gradients, detecting obstacles and controlling pre-fill operations based on gradient changes and time-to-collision calculations, incorporating pitch angle and obstacle detection for enhanced collision prevention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing ADAS uses standard TTC calculation based on current speed and acceleration, then the system is simple to operate, but the collision risk identification performance degrades when road gradient changes
Solution Approach 1:
The system performs preliminary detection of road gradient changes using camera-based lane line analysis before TTC calculation. By detecting gradient changes in advance and adjusting the TTC calculation accordingly, the system maintains reliable collision risk identification across varying road conditions without requiring completely new hardware or complex algorithms.
2Speed
If the system adjusts pre-fill operation based on road gradient detection, then the responsiveness to collision risk improves, but the device complexity increases due to additional sensors and processing
Solution Approach 1:
The camera system serves multiple functions: it captures images for both lane line detection (gradient detection) and obstacle identification. The processor performs multiple tasks including gradient calculation, TTC adjustment, and obstacle detection using the same image data. This multi-functionality approach improves responsiveness without proportionally increasing device complexity.
Solution Approach 2:
The system uses pitch angle information from the communicator as an intermediary parameter to verify gradient changes detected by lane line analysis. This intermediary check helps distinguish actual road gradient changes from vehicle motion effects, improving the reliability of gradient-based responsiveness adjustments without requiring direct additional sensing infrastructure.
3Adaptability or versatility
If the system uses camera image information and lane line distortion to detect gradient changes, then the adaptability to different road conditions improves, but the measurement precision may be affected by image processing limitations
Solution Approach 1:
The system employs feedback mechanisms where the processor continuously monitors lane line distortion in sequential images, compares detected gradient changes with pitch angle data from the communicator, and adjusts TTC calculations accordingly. This feedback loop refines gradient detection accuracy by cross-validating camera-based measurements with inertial sensor data, maintaining precision while achieving adaptability to various road conditions.
Data Source
AI summary
Disclosed herein are a system for autonomous emergency braking and a vehicle including the same. The system of the present disclosure includes a camera, and a processor configured to identify at least one of other vehicle and a lane line in an image based on image information acquired by the camera, determine whether a gradient of a front road for a vehicle to be entered changes to a reference gradient or more based on at least one of whether the other vehicle is present and whether the lane line is distorted, and control a pre-fill operation based on determining that the gradient of the front road changes to the reference gradient or more.