obstacle avoidance

Obstacle avoidance is a fundamental capability for autonomous mobile robots, ensuring safe navigation in dynamic and unstructured environments. This paper presents a novel approach to real-time obstacle avoidance based on an Artificial Potential Field Method (APFM) utilizing a hyperbolic secant function. A mathematical formulation of the proposed model is developed and analyzed. To validate the approach, a simulation framework was implemented using ROS 2, the Gazebo simulator, and the TurtleBot3 Burger platform.

the goal of this article is to present evaluation results for a proposed modification of the Artificial Potential Field Method (APFM). The mathematical model employs Laplace functions to compute repulsive fields to simplify calculations. Additionally, the study introduces a comprehensive evaluation framework using Gazebo and ROS2, designed to test various obstacle avoidance algorithms in simulated environments. Experiments have been conducted in a virtual room containing static obstacles of diverse shapes.

The possibility of using a neural network to implement a system of avoidance of obstacles on the road has been investigated. The algorithms based on which such a system can work has been reviewed, also the principle of learning of the neural network has been considered. In order to implement investigation the simulator based on Unity and ML Agents has been developed. Using simulator the efficiency of education and this neural network in different configurations has been investigated.