Implementasi Neural Network Untuk Kendali Gerak Mobile Robot Pembasmi Hama

Abstract

The agricultural sector is one of the most important economic sectors for Indonesia. However, agriculture itself is accompanied by a number of problems, one of which is pests that attack crops and cause crop failure. The use of robotics in agriculture can now overcome the limited capacity of farmers to monitor large land areas. Using an RC robot that can be controlled automatically via a cell phone monitor screen, human work is greatly facilitated. Artificial intelligence is implanted into a robot to improve the performance of an agricultural robot. This paper discusses designing a pest spraying robot with Neural Network applications for effective and efficient control inputs. The feasibility of the proposed method is proven by simulation conducted in Neuroph Studio and MobotSim. The simulation results show that neural network applications can effectively manage mobile robot movements with an error value of less than 0.1 to avoid the obstacles they encounter to reach the target.