Control method for compartment intelligent service robot travelling based on neural network

Abstract

The invention discloses a control method for the compartment intelligent service robot traveling based on the neural network. The method is divided into a training phase and a learning phase, in the training phase, a positioning base station sensor is arranged in a compartment, a robot body is provided with a camera and an infrared detector, position parameters of the robot body are collected as input variables, an SCFNN model architecture is established in the form of at least two input nodes and one output node, and a four-layer operation in an SCFNN model is conducted to obtain an inferenceoutput value; in the learning phase, the input node is subjected to structural learning to generate new rules and subjected to parameter learning to obtain an inference value, a connection weight, the mean value of a member function and the modifier of a standard deviation are corrected, and when each input node enters the SCFNN model, correction is conducted until the SCFNN model is learned. Themethod has the following advantages that the application of the SCFNN neural network can shorten the calculation period and optimize the robot travel distance and speed to achieve the improvement ofartificial intelligence.

Description

Technical field [0001] The invention relates to the learning field of robots, in particular to a method for controlling the travel of an intelligent service robot based on a neural network. Background technique [0002] The application of robots is becoming more and more widespread, permeating almost all fields. Mobile robots are an important branch of robotics. As early as the 1960s, research on mobile robots has begun. The research on mobile robots involves many aspects. Among them, the path planning technology of mobile robots is in a pivotal position. The so-called path planning technology is that the robot uses its own sensors to respond to the environment. It can plan a safe operation route by itself, and complete the task efficiently. At the same time, under the premise that the robot completes the task, the trajectory of the robot should be optimized as much as possible. [0003] Traditional path planning methods for mobile robots are template matching path planning techn...

AI Technical Summary

Problems solved by technology

[0005] However, the neural network method applied to robots is not perfect. Although it can generate real-time obstacle avoidance trajectories in static and dynamic environments, the movement speed of robots is relatively slow, and there is a problem of response delay, which affects other robots in dynamic environments. and these methods will increase with the number of input nodes and the number of hidden layers, the model structure will become more and more complex, the convergence speed of the network will become very slow, and there will be disadvantages of long operation cycle and high delay

Images