Virtual Parking Space for Automatic Parking Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic parking technologies face challenges in successfully identifying and parking vehicles in target spaces due to interference and GPS signal weaknesses, leading to reduced parking success rates and user experience.
Innovation Solution
The method involves establishing a virtual parking space based on predetermined position information from a parking lot map, planning an automatic parking path, and using environmental feature matching to determine the vehicle's position, ensuring safe and efficient parking even when GPS signals are weak or lost.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ultrasonic radar-based automatic parking technology is used to detect parking spaces, then the vehicle can identify parking spaces and determine availability, but the parking success rate decreases when target parking spaces cannot be identified due to interference
Solution Approach 1:
The patent introduces a pre-stored map of the parking lot as an intermediary information source. When ultrasonic radar detection fails to identify the target parking space due to interference, the system retrieves position information from the pre-stored map to determine the vehicle's location and guide parking, thereby maintaining high parking success rate despite interference conditions.
Solution Approach 2:
The patent performs preliminary actions by pre-storing the map of the parking lot including parking space positions and environmental features before the actual parking operation. This advance preparation ensures that when detection fails during parking, the system already has backup position information available to complete the parking task successfully.
2Measurement precision
If GPS-based positioning is used to determine vehicle position in the parking lot, then the vehicle can navigate to the target parking space, but positioning accuracy deteriorates when GPS signals are weak or lost
Solution Approach 1:
The patent uses environmental features from the pre-stored map as an intermediary reference system. When GPS signals are weak or lost, the system matches real-time sensor data (cameras, LIDAR) with the pre-stored environmental features to determine vehicle position, maintaining positioning accuracy without relying on GPS.
Solution Approach 2:
The patent creates a detailed copy of the parking lot environment including parking space positions, road layouts, and environmental features, stored in advance. This digital copy serves as a backup positioning reference when GPS fails, allowing the system to determine vehicle position by comparing sensor data with the stored environmental model.
3Ease of operation
If conventional automatic parking systems are used, then basic parking assistance is provided, but the system fails when target parking space detection is interfered with, reducing user experience
Solution Approach 1:
The patent performs preliminary actions by pre-storing comprehensive parking lot maps and environmental features before parking operations. This advance preparation creates a backup information system that ensures parking completion reliability when detection is interfered with, maintaining ease of operation even in challenging conditions.
Solution Approach 2:
The patent prepares compensatory measures in advance by storing alternative position information and environmental features. When the primary detection system fails due to interference, these pre-prepared backup resources activate to cushion the failure and maintain parking completion reliability, preventing degradation of user experience.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The present disclosure discloses an automatic parking method, a parking system, a computer device, and a storage medium. The method includes: obtaining, in response to a vehicle entering a parking lot, a map of the parking lot; determining, during a process of driving in the parking lot, whether the vehicle has reached a target parking region; establishing, in response to the vehicle reaching the target parking region, a virtual parking space based on position information of a target parking space predetermined in the map of the parking lot, and planning an automatic parking path based on the virtual parking space along with position information of the vehicle in the map of the parking lot; and parking the vehicle into the target parking space based on the automatic parking path. According to the present disclosure, by using the map corresponding to the parking lot to assist the vehicle in planning the automatic parking path after the vehicle enters the parking lot, efficient, flexible and safe automatic parking can be performed, which overcomes a defect in the related art that the vehicle cannot be parked in case the target parking space cannot be identified by the vehicle, improves use experience of a driver, and is suitable for large-scale promotion and application.