Autonomous Vehicle Path Library for Real-Time Local Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through complex environments like parking lots and narrow roads due to the difficulty in determining optimal paths, especially for articulated vehicles like tractor-trailers, which require high computational resources and precise path planning to avoid collisions and maintain stability.
Innovation Solution
The method involves generating a compact library of optimal paths offline using a grid node map and orientation grid bin map, performing an exhaustive search for optimal vehicle driving trajectories, and storing these paths on the vehicle for real-time navigation, reducing the computational load on onboard resources and enhancing path planning efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If exhaustive search is performed for optimal vehicle driving trajectories using grid node map and orientation grid bin map, then path planning precision is improved, but computational complexity increases
Solution Approach 1:
The patent pre-computes and stores optimal paths offline in a path library before real-time navigation. The grid node map and orientation grid bin map are processed in advance to generate pre-stored path segments, which are then retrieved and combined during actual navigation. This preliminary action transfers computational burden from online to offline processing, resolving the contradiction between precision and complexity.
Solution Approach 2:
The patent segments the continuous path planning problem into discrete grid nodes and orientation bins. By dividing the navigation space into manageable grid cells and pre-computing optimal transitions between them, the system achieves precise path planning through composition of pre-stored segments, reducing real-time computational complexity while maintaining accuracy.
2Speed
If real-time path planning is performed onboard the autonomous vehicle, then navigation responsiveness is improved, but hardware cost increases
Solution Approach 1:
The system performs path planning computations in advance and stores results in a pre-computed path library. During real-time navigation, the onboard system only needs to retrieve and combine pre-stored path segments based on current position and orientation, achieving rapid response with minimal hardware requirements. This resolves the contradiction by moving heavy computation offline.
Solution Approach 2:
The patent creates a simplified copy of the path planning problem in the form of a discrete grid node map and pre-computed path library. Instead of performing continuous optimization onboard, the system uses pre-stored discrete path segments that can be quickly retrieved and combined, reducing hardware costs while maintaining navigation responsiveness.
3Productivity
If pre-stored path library is used for navigation, then computational load is reduced, but path planning flexibility decreases
Solution Approach 1:
The patent segments the navigation space into grid nodes and orientation bins, creating a discrete path library that can be efficiently retrieved. The segmented structure allows flexible combination of pre-stored segments to adapt to different starting positions, orientations, and destinations while maintaining computational efficiency.
Solution Approach 2:
The system dynamically selects and combines appropriate pre-stored path segments based on real-time vehicle position, orientation, and destination. The path library structure enables flexible recombination of segments to create optimal paths for various scenarios, maintaining adaptability while utilizing pre-computed data for computational efficiency.
Data Source
AI summary
Methods, systems and apparatus for autonomous vehicle path planning and path navigation are described. One example system includes an offline server configured to generate a library of optimal paths for navigating a geographic area, wherein the geographic area is represented as a grid node map and an orientation grid bin map and wherein the optimal paths correspond to paths between pairs of grid node pairs in the grid node map based on optimization criteria, a storage device on the autonomous vehicle for storing the library of optimal paths, and an online server located on the autonomous vehicle configured to access information from the library of optimal paths from the storage device based on a current position and a current heading of the autonomous vehicle, and navigating the autonomous vehicle through the geographic area based on the information.