Vehicle Path Planning via Sub-path Segmentation and Cost Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for guiding vehicles into and out of parking spaces are limited by the need for pre-definition of path sections, require significant computing capacity, and often fail in practical applications due to these constraints.
Innovation Solution
A method that divides the path into linear sub-paths defined by an increment and steering angle, optimizing each sub-path independently using a cost function with weighted components for distance and angle difference, and adapting these weights based on the scenario to minimize computing power and ensure reliable navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If global optimization of the entire path is carried out, then path planning accuracy is improved, but computing power requirements increase
Solution Approach 1:
The patent divides the global path optimization problem into multiple local sub-path optimization problems. Each sub-path is optimized independently using a cost function that considers local distance and angle components, rather than optimizing the entire path globally. This segmentation reduces the computational complexity and energy requirements while maintaining sufficient path planning accuracy for parking maneuvers.
Solution Approach 2:
The patent employs dynamic weighting factors for the cost function components (distance component and angle component) that adapt based on the vehicle's current state and position. This dynamic adjustment allows the system to prioritize different optimization goals at different stages of the maneuver, achieving accurate path planning with reduced computational burden compared to static global optimization.
2Adaptability or versatility
If multiple linear and curved sections are predefined, then path planning versatility is improved, but device complexity increases
Solution Approach 1:
The patent represents the vehicle's path as a sequence of discrete sub-paths, where each sub-path is defined by simple parameters (distance increment and steering angle) rather than complex curve equations. This segmentation approach maintains versatility in handling different parking scenarios while reducing the complexity of path definition and computation.
Solution Approach 2:
The patent changes the parameter representation from traditional continuous curve definitions to discrete sub-path parameters (distance increment η and steering angle δ). This parameter transformation simplifies the path planning structure while maintaining the ability to adapt to various parking situations through optimized weighting factors in the cost function.
3Measurement precision
If manual path adjustment is required, then path accuracy is improved, but operation time increases
Solution Approach 1:
The patent implements a self-adjusting path planning system that automatically optimizes sub-paths using a cost function with adaptive weighting factors. The system independently adjusts the path parameters (distance and angle components) without requiring manual intervention, thereby maintaining high path accuracy while reducing the time loss associated with manual path adjustment.
4Device complexity
If computing capacity is limited, then device simplicity is maintained, but path optimization capability deteriorates
Solution Approach 1:
The patent segments the path optimization task into multiple independent sub-path optimizations, each handling a small portion of the overall maneuver. This segmentation enables the system to achieve effective path optimization with limited computing capacity, as each sub-problem requires minimal computational resources compared to global optimization.
Solution Approach 2:
The patent applies partial optimization to each sub-path rather than attempting full global optimization. By focusing computational effort on local sub-paths with adaptive weighting, the system achieves sufficient overall path optimization capability despite limited computing capacity, effectively performing 'enough' optimization without requiring excessive computational resources.
Data Source
AI summary
For steering a vehicle around obstacles, proceeding along a path from a starting position to an end position, the path including linear sub-paths which are defined by an increment η and a steering angle δ, a method includes: a) determining a maximum steering angle range and a maximum and a minimum increment range; b) determining the present distance eP from the end position, the target angle θO, and the angle difference eθ between the present vehicle angle and the target angle; c) performing an optimization method for ascertaining a sub-path by minimizing the value of a cost function lo assigned to the sub-path; d) determining the new position by adding the ascertained sub-path to the present position; and e) repeating steps (b) through (d) until the end position is reached.