Skip to content
naulon

Not checkedNot checked for notices yet.

Study of the genetic algorithm configuration for the autonomous robot pathfinding problem

В. Славгородський, С. Резніков

Adaptivni Sistemi Avtomatičnogo Upravlinnâ · 2022

doi:10.20535/1560-8956.40.2022.261653 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

The article is devoted to the development and improvement of the systems of formation of rational routes of mobile robots that use a genetic algorithm. For the functioning of the mobile robot it is necessary to solve the problem of route formation. This task is global, contains many solutions and does not require absolute precision. To solve this problem, a genetic algorithm is suitable, it is a heuristic algorithm of global search. This algorithm operates with different genetic operators, such as crossover, mutation, selection, generation of populations and generations. These operators can be adapted to the need for route search. Thus, the genotype as a value that can operate on the algorithm can be represented as a route consisting of distant from each other waypoints. Then, with the help of genetic operators, routes are created and changed until a route is found, it should avoid various navigational hazards and satisfies the specified parameters. However, the search engine itself depends on the coefficients that determine the mode of operation of genetic operators. The effectiveness of this method of solving the navigation problem directly depends on the selected factors that make solving the problem fast and reliable or completely ineffective the algorithm. Thus, before the direct application of the algorithm, it is necessary to identify the basic patterns between the coefficients used, as well as to determine their optimal values, which will be most effective for the algorithm. Ref. 5, pic. 8.

Abstract licence: CC BY

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.