Aerial Vehicle Trajectory Planning With Seeded Obstacle Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current trajectory planning methods for aerial vehicles are inefficient due to frequent computation needs and reliability issues with obstacle avoidance, particularly in dynamic environments.
Innovation Solution
A system and method that uses a sensor payload and processor to calculate path trajectory segments, identify seed waypoints, and execute a random searching algorithm, such as the rapidly exploring random tree algorithm, to generate obstacle-avoiding trajectories for aerial vehicles, incorporating iterative Dubins path calculations and smoothing algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If current trajectory planning methods link together approximations of short trajectories by geometric arcs and line segments, then the trajectory can be generated, but the computation time is excessive and frequent updates are needed
Solution Approach 1:
The trajectory planning is divided into multiple short trajectory segments that are pre-calculated and stored. Instead of computing the entire trajectory at once, the system segments the path and retrieves pre-computed segments, significantly reducing real-time computation time while maintaining trajectory accuracy.
Solution Approach 2:
Trajectory segments are pre-calculated and stored in a database before actual navigation. This preliminary computation allows the system to quickly retrieve and assemble trajectories during flight without performing heavy calculations in real-time, improving both computation speed and efficiency.
2Reliability
If current trajectory planning methods are used, then trajectories can be generated, but obstacle avoidance reliability is insufficient
Solution Approach 1:
The system continuously monitors the vehicle's position and compares it with the planned trajectory and detected obstacles. When obstacles are detected or deviations occur, the system provides feedback to recalculate and adjust the trajectory segments, ensuring reliable obstacle avoidance through continuous closed-loop control.
Solution Approach 2:
The trajectory planning system dynamically adapts to changing environments by updating trajectory segments based on real-time obstacle detection and vehicle state. The system transitions from static pre-computed paths to dynamic re-planning, maintaining reliability in dynamic environments while managing complexity through efficient algorithms.
3Stability of the object's composition
If frequent updates are performed in current trajectory planning methods, then the trajectory tracking can be maintained, but the computation time increases significantly
Solution Approach 1:
The trajectory is divided into discrete segments that can be independently updated. Instead of recalculating the entire trajectory during updates, only the affected segments are recomputed and replaced, maintaining tracking stability while minimizing computation time through localized updates.
Solution Approach 2:
Multiple trajectory segments are pre-calculated for different scenarios and conditions. During operation, the system selects and assembles appropriate pre-computed segments based on current state, avoiding the need for frequent full-trajectory recalculations and reducing computation time while maintaining stability.
Data Source
Figure 1
Figure 2a~2b
Figure 2c
AI summary
The present disclosure is directed to systems and methods for trajectory and route planning including obstacle detection and avoidance for an aerial vehicle. For example, an aerial vehicle's flight control system may include a trajectory planner that may use short segments calculated using an iterative Dubins path to find a first path between a start point and an end point that does not avoid obstacles. Then the trajectory planner may use a rapidly exploring random tree algorithm that uses points along the first path as seed points to find a trajectory or route between the start point and end point that avoids known or detected obstacles.