Automatic Parking Path Planning with Cropped Space Boundaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic parking path planning methods require large spaces and have low success rates and efficiency due to limitations in specific parking environments.
Innovation Solution
Cropping the ground and road sidelines to define available parking space boundaries, allowing collision with ground sidelines during path planning, and performing collision detection based on these boundaries to optimize parking paths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional parking path planning methods (real-time arc method or HybridA* search algorithm) are used, then a complete parking place boundary is taken as parking boundary for collision detection, but a large space is required and planning success rate is low
Solution Approach 1:
The parking space boundary is segmented into two parts: ground sideline (where collision is allowed) and actual obstacle contour line (where collision is not allowed). This segmentation allows the path planning to utilize the ground sideline area while still avoiding real obstacles, thereby increasing the available planning space and improving success rate without requiring additional parking space.
Solution Approach 2:
Different parts of the boundary are assigned different collision properties: the ground sideline portion allows vehicle body collision while the actual obstacle contour line portion prohibits collision. This local differentiation enables the vehicle to use the ground area for path planning while maintaining safety around actual obstacles, resolving the contradiction between space utilization and collision avoidance.
2Productivity
If a complete parking place boundary is used for collision detection, then safety is maintained, but parking efficiency is low due to large space requirements
Solution Approach 1:
By segmenting the boundary into ground sideline and actual obstacle contour line, the method enables more aggressive space utilization during path planning while maintaining safety. The vehicle can plan paths that utilize the ground sideline area, reducing the effective space needed for parking operations and improving parking efficiency.
Solution Approach 2:
The collision detection parameters are changed by introducing different collision allowances for different boundary segments. Instead of a uniform no-collision policy, the system allows collision with ground sideline while prohibiting collision with actual obstacles, enabling more efficient space utilization and faster parking operations.
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
The present disclosure provides a method and an apparatus for planning an automatic parking path, a medium and a device and belongs to the field of self driving technologies. The method includes: extracting perception information within a predetermined parking space including a target vehicle place, which is perceived by a vehicle; based on the perception information, identifying a ground sideline of the target parking place, a road sideline and an actual obstacle contour line; cropping the ground sideline and the road sideline intersecting with the ground sideline and taking remaining ground sideline and road sideline as corresponding boundaries of an available parking space of the target parking place; and, performing collision detection based on the corresponding boundaries of the available parking space and the actual obstacle contour line, and based on a result of the collision detection, performing vehicle trajectory planning to obtain an automatic parking planning path. The present disclosure can provide an automatic parking process in a specific environment with a larger free parking space as compared with the prior art, so as to improve a success rate of planning an automatic parking path, and improve a parking efficiency.