Swarm-Based Approach to Path Planning Using Honey-Bees Mating Algorithm and ART Neural Network

Abstract

In this paper, an integration of Honey bees mating algorithm (HBMA) and adaptive resonance theory neural network (ART1) for efficient path planning of a mobile robot in a static environment is presented. The robot must find shortest route from given origin to the target position. Moreover, it should be able to memorize the environment and, if it faces known world, execute already learned trajectory found by HBMA solver, or solve the world and memorize the trajectory for the given environment. This is done using Adaptive Resonance Theory based neural network. This way simulated robot is able to navigate through environment and to continuously increase its knowledge.

Evolutionary Planner of 3D Trajectories

“…Furthermore, they are tested on the same labyrinths with the same obstacle placements and starting and goal positions. The population is a matrix (1), (2), where m represents the number of individuals and n represents the length of the genome. Population size m is set to 50 members in each algorithm, while genome length n is set to 10 which is the required number of steps from the start to the end of the labyrinth with no collisions.…”

“…In this paper, an evolutionary algorithm is used to test how different diversity maintenance methods affect speed and the level of convergence of the algorithm. In order to do that, the algorithm was used to find the solution of a difficult real-world problem [1], [2], [3], [4]: find a feasible and optimized path inside of 2D and 3D space filled with obstacles. The pathway must end in the designated area, and it is not allowed to have collisions with obstacles.…”

Legged 3D Printed Mobile Robot

“…Their movement becomes nonintuitive; accordingly, it requires more sophisticated control and learning algorithms. In such demanding applications, artificial intelligence algorithms surpass performance of human engineers [2], [3], [4]. Having that in mind, we chose to reconstruct quadruped robotic platform with counter-intuitive gait mechanism.…”

Bayesian Approach to Robot Group Control

“…Ubicomp applications are normally envisioned to be sensitive to context, where context can include an object's location, activity, goals, resources, state of mind, and nearby people and things. Ubiquitous computing involves many different research areas, e.g., Distributed Computing, Mobile Computing [3], Sensor Networks, Human-Computer Interaction, Artificial Intelligence [4], etc. In an automatic assembly, the control of a system is usually connected to the control of the working environment.…”