Vehicle Path Guidance Using Prioritized Obstacle Boundary Waypoints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing path finding techniques for autonomous vehicles are inefficient in real-time applications due to high computational requirements for analyzing obstacles and finding valid paths, especially in complex environments, as they build full visibility graphs without prioritizing important information.
Innovation Solution
A computer-implemented method that constructs a visibility graph efficiently by filtering non-essential information and prioritizing candidate waypoints using a heuristic to reduce unnecessary waypoints and subpaths, employing geometric descriptions and common tangents to simplify the path finding process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional visibility graph construction is used to ensure complete obstacle avoidance, then path finding reliability is improved, but computational time and processing power requirements increase significantly
Solution Approach 1:
The patent segments the complete visibility graph construction into two phases: an offline preprocessing phase that builds a comprehensive visibility graph storing all visibility relationships between polygons, and an online query phase that quickly retrieves pre-computed paths. This segmentation allows the computationally intensive graph construction to be performed once, while real-time path queries benefit from the pre-organized data structure without repeating the full construction process.
Solution Approach 2:
The patent performs preliminary action by pre-computing and storing the complete visibility graph before actual path finding operations. All visibility relationships between obstacles are calculated in advance and stored in a data structure that enables rapid querying. This preliminary computation eliminates the need to re-calculate visibility relationships during real-time path finding, significantly reducing online computational time while maintaining complete obstacle avoidance reliability.
2Measurement precision
If all polygon vertices are considered as potential waypoints to ensure complete path coverage, then path finding accuracy is improved, but device complexity and computational resources increase
Solution Approach 1:
The patent extracts only the essential visibility relationships from the complete set of polygon vertices. Instead of treating all vertices as potential waypoints, the system identifies and stores only those visibility edges that are necessary for optimal path finding. This extraction process reduces the number of nodes and edges in the visibility graph while preserving the ability to find accurate paths by removing redundant vertices that do not contribute to optimal routes.
3Reliability
If full visibility graphs are constructed to provide complete path information, then path optimality is ensured, but memory usage and processing power requirements increase
Solution Approach 1:
The patent applies local quality by optimizing the visibility graph storage to contain only the specific visibility relationships relevant to the given scenario. Instead of uniformly storing all possible visibility edges between all polygons, the system identifies and stores only those local visibility relationships that are necessary for finding optimal paths in the specific environment. This localized approach reduces memory requirements while preserving path optimality by maintaining the essential connectivity information.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method and a system for guiding a vehicle from a source to a target within a scenario with obstacles are disclosed. The source is established as a starting point and a subpath to the target is computed. When an obstacle is detected that crosses the computed subpath, a plurality of obstacle-free subpaths are computed to connect the starting point to a waypoint of an outer boundary of a detected obstacle. Priorities for each waypoint are computed and ordered accordingly in a list of potential waypoints to select the highest priority waypoint in the list as a new starting point. Previous operations are repeated until the target is reached, thus the path is obtained by backtracking waypoints to the source. The vehicle can be then guided and the target reached via the obtained path.