Parking Assistance Trajectory Selection Using Camera Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking assistance systems face challenges in distinguishing between multiple learned trajectories, especially when used by different users, leading to confusion and inefficient parking maneuvers due to the lack of intuitive user interface for trajectory selection.
Innovation Solution
A method and system that utilizes on-board camera images to capture and store trajectories as sequences of positions with associated images, allowing users to select the desired trajectory intuitively through a display interface, eliminating the need for metadata and enhancing user reliability in selecting the correct path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple trajectories are stored in the parking assistance system, then the system can handle various parking situations, but users cannot easily distinguish and select the correct trajectory
Solution Approach 1:
The patent uses image copies (photographs) of the target positions from each trajectory as identifiers in the user interface. Instead of using abstract metadata or labels, the system displays actual visual copies of what the target position looks like, allowing users to intuitively recognize and select the correct trajectory by matching the displayed image with their memory of the destination.
2Loss of information
If metadata such as keywords and descriptions are assigned to trajectories, then trajectories can be distinguished, but the system becomes complex and memory requirements increase
Solution Approach 1:
Instead of creating and storing abstract metadata (keywords, descriptions, labels), the system directly uses copies of the existing camera images captured during trajectory recording as the identification mechanism. This eliminates the need for separate metadata storage structures while providing rich visual identification information.
Solution Approach 2:
The images captured during normal trajectory recording serve dual purposes: they document the visual appearance of the target position for identification purposes and are already part of the trajectory data structure. The system repurposes existing data (the captured images) for the additional function of trajectory identification, avoiding redundant data storage.
3Reliability
If detailed metadata is stored for each trajectory, then trajectories can be uniquely identified, but memory requirements and data storage increase
Solution Approach 1:
The images captured during trajectory recording serve dual purposes: they document the visual appearance of the target position for identification purposes and are already part of the trajectory data structure. The system repurposes existing data (the captured images) for the additional function of trajectory identification, avoiding redundant data storage.
Data Source
AI summary
A method for operating a parking assistance system for a vehicle, where the parking assistance system autonomously tracks a trajectory from a number of trajectories learned in a training mode. The respective trajectory is determined by a sequence of positions and connects a starting position to a target position. The respective trajectory is assigned a number of images of an environment of the vehicle captured by the vehicle's camera in the respective position and stored. The method includes providing a number of stored images; determining a display element having the provided images to represent the respective associated trajectory; outputting the determined display element to a display device of a user interface of the vehicle; receiving a user input for selecting at least one image contained in the display element via the user interface; and initiating an autonomous journey of the vehicle along the trajectory associated with the selected image.