Automatic Parking Path Planning for Area-Aware Maneuver Costs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional automatic parking solutions lack diversity in parking path planning, resulting in paths that significantly differ from manual parking, leading to poor user experience due to unexpected obstacles, gear shifts, and steering difficulties.
Innovation Solution
An automatic parking method that considers the type and location of candidate path points within different areas, evaluating costs for gear shifts, steer angles, and obstacle types to plan a parking path that minimizes unexpected areas and aligns with user driving habits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If conventional automatic parking path planning is used, then parking automation is achieved, but the planned path differs greatly from manual parking paths, resulting in poor user experience
Solution Approach 1:
The patent applies local quality by differentiating path planning based on the type of area (e.g., grass area, crossable curb, crossable pit) where candidate path points are located. By assigning different costs to passing through different area types, the system generates parking paths that locally adapt to environmental characteristics, making the automatic parking behavior more similar to manual parking decisions and improving user experience.
2Reliability
If diverse area types are considered in path planning, then parking path quality improves, but calculation complexity increases
Solution Approach 1:
The patent segments the parking environment into distinct area types (grass area, crossable curb, crossable pit, etc.) and assigns specific cost values to each type. This segmentation approach simplifies the complexity by categorizing continuous environmental variations into discrete types, making the path planning calculation more manageable while still capturing the essential differences in passing costs through different areas.
3Object-affected harmful factors
If unexpected areas like grass or crossable curbs are avoided, then collision risks are reduced, but parking path options are limited
Solution Approach 1:
The patent changes the parameter of passing cost based on the type of area being considered. Instead of treating all areas uniformly or simply avoiding unexpected areas, the system assigns different cost parameters to different area types (e.g., higher cost for grass areas, lower cost for crossable curbs). This allows the path planning to flexibly select appropriate paths by comparing costs, reducing collision risks while maintaining path planning versatility.
Data Source
Figure 1~2
Figure 3
Figure 4(a)~5
AI summary
An automatic parking method and apparatus are provided. The method includes: obtaining a first candidate path point and a second candidate path point, where the first candidate path point is located in a first area, and the second candidate path point is located in a second area; determining a first cost based on a type of the first area and a location relationship between the first candidate path point and the first area, and determining a second cost based on a type of the second area and a location relationship between the second candidate path point and the second area; and planning a parking path based on the first cost and the second cost. The automatic parking apparatus, an automatic parking system, and a vehicle (100) that use the method are further provided. A parking path is planned based on a type of an area in which a candidate path point is located, so that a possibility that a vehicle passes in an area like a grass, a crossable curb, or a crossable pit can be reduced, and automatic parking experience can be improved.