Vehicle Path Planning Using 2D+t Obstacle Interception Polygons
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current path-finding algorithms for autonomous vehicles, such as UAVs and ground robots, are inefficient in real-time applications, especially when dealing with static and dynamic obstacles that change shape or position, leading to slow processing and potential collisions.
Innovation Solution
The proposed method generates conflict-free paths by representing obstacles in a 2D+t space using polytopes and velocity cones, allowing for efficient computation of interception polygons and visibility graphs to guide vehicles around static and dynamic obstacles, incorporating heuristic and geometric algorithms to reduce computational demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional path-finding algorithms are used to handle static and dynamic obstacles, then collision avoidance is achieved, but processing speed is too slow for real-time applications
Solution Approach 1:
The algorithm segments the continuous space into discrete cells and the path planning into hierarchical levels (global path planning followed by local path adjustment). This segmentation allows parallel processing of multiple cells and reduces computational complexity, enabling real-time performance while maintaining collision avoidance reliability.
Solution Approach 2:
The patent introduces a time dimension to the traditional 2D path planning, creating a 3D configuration space (x, y, t) where dynamic obstacles are represented as time-varying constraints. This dimensional transformation allows the algorithm to handle dynamic obstacles efficiently by treating them as static constraints in the extended space, improving processing speed without sacrificing collision avoidance.
2Reliability
If comprehensive obstacle tracking and path recalculation is performed, then navigation safety is improved, but computational complexity increases
Solution Approach 1:
The algorithm performs preliminary global path planning in the 3D configuration space before execution, pre-calculating safe corridors and avoidance regions. During real-time operation, only local adjustments are needed based on current obstacle positions, significantly reducing computational complexity while maintaining navigation safety through the pre-computed safe paths.
Solution Approach 2:
The path planning algorithm dynamically adapts to changing obstacle configurations by continuously updating the configuration space representation and recalculating paths only when necessary. The system transitions between static global planning and dynamic local adjustment, optimizing computational complexity while ensuring navigation safety through continuous adaptation.
Data Source
Figure 1~3
Figure 4A~5
Figure 6~7
AI summary
A computer-implemented method and a system for generating a path for a vehicle from a source to a target within a 2D environment with one or more obstacles is disclosed. The obstacles may be dynamic, static or both. The method comprises generating, in a 2D + t space, a velocity cone that represents a set of potential waypoints reachable from a first source for the vehicle moving at a first speed, providing a polytope, obtaining at least one interception polygon by intersecting and projecting the velocity cone with the polytope on the 2D region; generating a 2D scene comprising interception polygons to avoid, computing a visibility graph algorithm for the 2D scene and obtaining a plurality of conflict-free sub-paths, composing a valid path connecting the source to the target based on the plurality of conflict-free sub-paths.