Parking Assist Sensor Fusion for Off-FOV Obstacle Steering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional remote smart parking assist systems face challenges in accurately determining the longitudinal position of objects outside their field of view due to limitations in ultrasonic sensor field of view, leading to inaccurate avoidance steering during autonomous parking.
Innovation Solution
A parking assist system that combines sensor fusion of ultrasonic sensing data with surround view monitor camera image data to calculate object positions and perform precise avoidance steering, using a sensor fusion calculation module to correct object positions and determine optimal avoidance reference points for steering control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ultrasonic sensor is used for object detection in autonomous parking, then the system can detect surrounding objects, but the field of view is limited and longitudinal position accuracy deteriorates for objects outside the sensor's field of view
Solution Approach 1:
The patent combines ultrasonic sensor data with camera image data through sensor fusion to detect objects. The ultrasonic sensor provides reliable detection of surrounding objects while the camera supplements positional information for objects outside the ultrasonic sensor's field of view, resolving the contradiction between detection reliability and measurement precision
Solution Approach 2:
The patent introduces a camera as an intermediary device to bridge the gap in longitudinal position measurement. When an object is detected by the ultrasonic sensor but lies outside its field of view, the camera captures the object's position in the image data, which is then used to calculate accurate longitudinal position through coordinate transformation
2Ease of operation
If avoidance steering is performed based on inaccurate longitudinal position data, then the parking assist system can execute steering control, but the avoidance steering becomes unrobust and unreliable
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors object positions using both ultrasonic sensors and cameras. When objects are detected outside the ultrasonic field of view, the system uses camera-based positional information to correct and refine the longitudinal position data, ensuring robust avoidance steering control
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 accuracy of object detection and avoidance steering, enabling safer and more reliable autonomous parking by compensating for the limited field of view of ultrasonic sensors with wider and more directional image data from the surround view monitor.
Implementation Method 1
a sensor module that detects a distance from a vehicle and an object using sensing data obtained by scanning the periphery of the vehicle
Implementation Method 2
detects a distance from a vehicle and an object using sensing data obtained by scanning the periphery of the vehicle
Implementation Method 3
a surround view monitor (SVM) camera that captures an image around the vehicle to obtain image data capable of detecting a position and a direction of the object
Data Source
AI summary
A parking assist system with improved avoidance steering control and a method thereof are provided. The parking assist system includes a sensor fusion calculation module that fuses sensing data of an ultrasonic sensor and image data of an SVM camera to calculate position information of an object with respect to a current location of a vehicle and a parking assist module that avoids the object based on the position information and performs steering control of the vehicle for autonomous parking. The parking assist system accurately detects the object on a position departing from a field of view (FOV) of the ultrasonic sensor and performs avoidance steering robust to a surrounding object upon autonomous parking.