Optimal Route Searching for Autonomous Valet Parking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous valet parking systems inefficiently search for parking spaces due to lack of global route planning, leading to suboptimal vehicle navigation and increased driving costs.
Innovation Solution
An optimal route searching device using a cost function-based route search algorithm that processes map information, transforms topology, and calculates travel costs to determine the lowest-cost route for finding a vacant parking space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If simple front recognition is used to find parking spaces, then the system is easy to operate, but the vehicle driving efficiency is poor and global route planning is not considered
Solution Approach 1:
The patent segments the parking area into multiple sub-areas divided by virtual walls, and further divides routes into multiple segments. This allows the system to plan global routes while maintaining simple local navigation operations, resolving the contradiction between ease of operation and driving efficiency.
Solution Approach 2:
The patent introduces a vertical dimension by creating virtual walls that divide the 2D parking area into multiple sub-areas. This dimensional transformation enables global route planning while keeping the navigation system operationally simple, as the vehicle only needs to navigate within defined segments rather than continuously searching the entire area.
2Productivity
If global route planning is implemented to find parking spaces efficiently, then vehicle driving efficiency is improved, but the system complexity increases
Solution Approach 1:
The patent divides the complex parking area into multiple simple sub-areas separated by virtual walls. This segmentation reduces the complexity of global route planning by breaking down the navigation problem into smaller, manageable segments, allowing efficient planning without excessive system complexity.
Solution Approach 2:
The patent introduces virtual walls as intermediary elements that define sub-areas and guide route planning. These virtual walls act as mediators between the global route planning algorithm and the actual vehicle navigation, simplifying the system architecture while enabling efficient global planning.
3Measurement precision
If multiple candidate routes are evaluated using cost functions, then the optimal parking space is found with lowest cost, but the calculation time and processing complexity increase
Solution Approach 1:
The patent segments the parking area into sub-areas using virtual walls, which reduces the number of candidate routes that need to be evaluated. By dividing the search space, the system can find optimal routes more quickly, resolving the contradiction between route optimality and calculation time.
Solution Approach 2:
The patent assigns different costs to different types of routes and sub-areas based on local characteristics. This local quality approach allows the system to prioritize certain routes over others during evaluation, reducing the time needed to find optimal paths while maintaining measurement precision.
Data Source
AI summary
An operation method of an optimal route searching device includes: acquiring topology transformed map information; extracting a plurality of candidate routes based on the topology transformed map information; calculating a travel cost for each of the plurality of candidate routes based on a cost function; and determining a candidate route corresponding to a lowest cost one of the calculated travel costs as a travelling route.