The dynamic autonomous collision avoidance of the unmanned ship can quickly avoid sudden or high-speed obstacles in the surrounding environment based on sensor data, so as to ensure the safety of the unmanned ship during navigation. Commonly used dynamic autonomous collision avoidance algorithms include artificial potential field method, dynamic window method, speed obstacle method, vector field histogram method, etc. The existing collision avoidance algorithm still has the following problems :
(1) The algorithm does not combine the international rules for avoiding collisions at sea, resulting in collision avoidance failures or secondary accidents.
(2) The algorithm does not consider the maneuvering characteristics of the unmanned ship, which makes it difficult to apply the planned collision avoidance path to the actual navigation of the unmanned ship.
(3) The algorithm has a large amount of calculation, and it cannot realize the rapid collision avoidance of high-speed unmanned ships in complex sea conditions.
It is time-consuming and labor-intensive to verify the algorithm with real ships, and the cost is very high. In addition, local obstacles in the environment may be very changeable during the navigation of unmanned ships, and it is also very complicated to build local obstacles that meet the requirements. Therefore, it is considered to use Matlab to build a simulation platform for the local collision avoidance algorithm of unmanned ships.
1. Interface
Open the main program in the Matlab environment and click the run button
The following window will pop up
The window can be used to set the running algorithm, including "algorithm selection" and "step size setting". After confirmation, click "start sailing" to enter the simulation running environment of the collision avoidance algorithm. "Algorithm selection" includes the following:
download link