Unmanned Vehicle Path Planning Using Reused State Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned vehicles face challenges in planning efficient paths in real-time, especially when navigating through areas with obstacles, as existing methods require frequent updates to avoid collisions and delays, leading to increased computational load and reduced path planning efficiency.
Innovation Solution
Implementing a method that reuses previously calculated vehicle-state data to reduce path planning time, allowing for the evaluation of more paths within a given timeframe by storing and retrieving feasibility and weight data for overlapping segments, thereby enhancing navigation efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If path planning is performed in real-time with frequent map updates to avoid obstacles, then navigation reliability is improved, but path planning time increases and efficiency decreases
Solution Approach 1:
The system pre-calculates and stores vehicle-state data (feasibility and weight information) in a data structure before actual path planning is needed. When planning a path, the system retrieves previously calculated data instead of recomputing it, significantly reducing real-time computational load while maintaining navigation reliability through frequent map updates.
Solution Approach 2:
The patent applies local quality by evaluating and storing data only for specific vehicle-states (local portions of the state space) that are relevant to the current navigation context. The data structure stores feasibility and weight information for discrete vehicle-states, allowing the system to efficiently query and reuse calculations for overlapping path segments without computing entire paths from scratch.
2Manufacturing precision
If more paths are evaluated within a given timeframe to increase the probability of finding a suitable path, then path quality is improved, but computational load increases
Solution Approach 1:
The system performs preliminary calculation of vehicle-state feasibility and weight data, storing results in a data structure for later retrieval. This allows multiple paths to be evaluated quickly by reusing previously computed data for overlapping segments, increasing the number of paths that can be assessed within a timeframe without proportionally increasing computational load.
Solution Approach 2:
The patent creates a data structure that copies and stores vehicle-state evaluation results (feasibility flags and weight values) for reuse. When planning multiple paths, the system copies previously calculated vehicle-state data rather than recalculating it, enabling efficient evaluation of numerous paths while reducing repetitive computational operations.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
Thus, according to some examples of the presently disclosed subject matter, in order to reduce path planning time, information that has previously been calculated during planning of a path is reused during planning of other subsequent paths. Using the stored indication reduces time required for planning the path and thus enables to evaluate a greater number of optional paths within a given period of time. This can assist in increasing speed and smoothness of vehicle maneuverability.