Neural network-based approaches for mobile robot navigation in static and moving obstacles environments

Mobile robots can travel by acquiring the information using sensor-actuator control techniques from surrounding and perform several tasks. Due to the ability of traversing, mobile robots are used in different application for different places. In the field of robotic research, robot navigation is the fundamental problem and it is easier in static environment than dynamic environment. This paper presents a new method for generating a collision-free, near-optimal path and speed for a mobile robot in a dynamic environment containing moving and static obstacles using artificial neural network. For each robot motion, the workspace is divided into five equal segments. The multilayer perceptron (MLP) neural network is used to choose a collision-free segment and also controls the speed of the robot for each motion. Simulation results show that the method is efficient and gives near-optimal path reaching the target position of the mobile robot.