Autonomous Path Planning Using Offline Graphs in Dynamic Environments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current path planning algorithms for vehicles in dynamic environments are computationally limiting due to the generation of large graphs, leading to suboptimal solutions and abnormal system behavior, as they fail to converge to near-optimal paths efficiently.
Innovation Solution
The method involves generating an offline graph representing feasible transitions and static obstacles, and an online graph that updates in real-time to account for dynamic obstacles, allowing for a non-exhaustive search to determine a path from the current position to a destination without extensive memory allocation, enabling the vehicle to adapt to new information while maintaining long-run goals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If rapidly exploring random algorithms are used to generate graphs for path planning in dynamic environments, then the system can operate online in soft real time, but the graph creation step requires an excessive amount of time and computational resources
Solution Approach 1:
The patent segments the path planning process into two distinct phases: an offline phase where a comprehensive graph is pre-computed using rapidly exploring random algorithms, and an online phase where only minimal updates are performed. This segmentation allows the computationally intensive graph generation to be done beforehand, while real-time operation requires only simple graph annotations and searches, thus resolving the contradiction between comprehensive path planning and real-time performance.
Solution Approach 2:
The patent applies preliminary action by pre-generating the complete path planning graph offline before the vehicle operates in the dynamic environment. This preliminary graph contains all feasible paths and transitions, so that during online operation, the system only needs to annotate the graph with current state information and perform efficient searches, avoiding the time-consuming graph generation step during critical real-time operations.
2Manufacturing precision
If large graphs are created to ensure near-optimal path solutions, then path planning accuracy improves, but the computational time and memory requirements become excessive
Solution Approach 1:
The patent segments the computational workload by performing the intensive graph generation offline and only performing lightweight operations online. The large, comprehensive graph ensures near-optimal path solutions, while the segmentation of computation allows this accuracy to be achieved without excessive real-time computational complexity.
Solution Approach 2:
The patent creates a computational copy of the environment in the form of a graph structure that can be manipulated virtually. This graphical representation allows the system to explore and evaluate numerous paths in silico, ensuring high path planning accuracy without requiring proportional physical computational resources during real-time operation, as the heavy lifting was done during offline graph creation.
3Loss of time
If small and shallow graphs are created to reduce computational burden, then processing time decreases, but the path planning algorithms fail to converge to near-optimal solutions
Solution Approach 1:
The patent performs the action of creating comprehensive graphs in advance during an offline phase, allowing small and shallow graphs to be used during online operation. This preliminary action ensures that near-optimal solutions are available while keeping real-time processing time minimal, as the online phase only requires simple graph annotations and searches rather than exhaustive graph generation.
Data Source
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.