Marine garbage recovery planning method and system based on machine vision and reinforcement learning
The invention discloses a marine garbage recovery planning method and system based on machine vision and reinforcement learning. The method comprises the steps: carrying out target detection on marine floating garbage through a target detection algorithm to obtain target data, wherein the target dat...
Gespeichert in:
Hauptverfasser: | , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a marine garbage recovery planning method and system based on machine vision and reinforcement learning. The method comprises the steps: carrying out target detection on marine floating garbage through a target detection algorithm to obtain target data, wherein the target data comprises the information of the number, type, position and distance of the marine floating garbage; establishing a target linear system according to the target data; and according to the target linear system, determining a marine garbage recovery planning strategy, and according to the marine garbage recovery planning strategy, cleaning the marine floating garbage. According to the invention, the marine garbage recovery efficiency is improved, energy consumption control is introduced, energy consumption can be reduced, the cruising ability of equipment is improved, and the method and system can be widely applied to the technical fields of artificial intelligence, marine garbage treatment and the like.
本发明公开了基于机器 |
---|