Autonomous Vehicle Path Planning for Dynamic Obstacles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current path planning algorithms for vehicles, especially in dynamic environments, face computational limitations due to the time-consuming process of generating large graphs, leading to suboptimal solutions and abnormal system behavior.
Innovation Solution
The method involves generating an offline graph representing feasible transitions around static obstacles and augmenting it with vertex-wise information. An online graph is then created by connecting the vehicle's current position to the offline graph, allowing for the evaluation of edge validity and dynamic obstacles, and performing a non-exhaustive search to determine a minimal path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If large graphs are generated using rapidly exploring random algorithms, then path planning completeness is improved, but computational time increases excessively
Solution Approach 1:
The patent segments the path planning process into two distinct phases: (1) an offline phase where a comprehensive graph is pre-computed avoiding static obstacles, and (2) an online phase where only dynamic obstacle avoidance is handled. This segmentation allows the computationally intensive graph generation to be performed once offline, while the online phase requires minimal computation for real-time responsiveness.
Solution Approach 2:
The patent performs preliminary action by pre-computing the complete graph structure, vertex representations, and edge connections in an offline phase before the vehicle operates in the dynamic environment. This preliminary computation ensures path planning completeness is established in advance, eliminating the need for time-consuming graph generation during real-time operation.
2Productivity
If small and shallow graphs are created to reduce computational time, then system responsiveness is improved, but path planning algorithms fail to converge to near-optimal solutions
Solution Approach 1:
The patent segments the graph into an offline component (complete graph with all static obstacle avoidance paths) and an online component (dynamic obstacle adjustments). This allows the system to use a shallow online graph for fast responsiveness while relying on the comprehensive offline graph for near-optimal path convergence.
Solution Approach 2:
By performing preliminary computation of the complete graph structure offline, the system establishes all possible optimal paths in advance. During online operation, the system only needs to make minor adjustments to these pre-computed paths to avoid dynamic obstacles, ensuring both optimality and responsiveness.
3Adaptability or versatility
If the graph is updated frequently to account for dynamic obstacles, then adaptability to new information is improved, but computational overhead increases
Solution Approach 1:
The patent segments obstacle handling into static obstacles (processed offline in graph construction) and dynamic obstacles (processed online with minimal computations). This segmentation allows frequent adaptation to dynamic obstacles without requiring frequent full graph regenerations, thus reducing computational overhead while maintaining high adaptability.
Solution Approach 2:
By pre-computing the graph structure offline with all static obstacle information embedded, the system eliminates the need for frequent online graph updates. Only minimal online adjustments are needed when dynamic obstacles are detected, significantly reducing computational overhead while maintaining adaptability.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Techniques for traversing in an environment that includes at least one obstacle, by a mobile autonomous system, to a destination in the environment, are presented. The techniques can include generating, prior to the mobile autonomous system commencing activity in the environment, a graph including a plurality of vertices representing positions in the environment and a plurality of edges between vertices representing feasible transitions by the mobile autonomous vehicle in the environment; annotating the graph with at least one edge connecting a representation of a present position of the mobile autonomous system to a vertex of the graph; determining, based on the graph, a path from the present position of the mobile autonomous system in the environment to the destination; and traversing the environment to the destination, by the mobile autonomous system, based on the path.