10.46243/jst.2024.v9.i1.pp50-60 registered

Robot navigation is a crucial aspect of robotics, enabling autonomous robots to move safely and efficiently through their surroundings. Conventionally, engineers and programmers have relied on fixed rules and heuristics to guide robot movements. However, these rules are often specific to certain environments and struggle to adapt to new or changing conditions. For instance, simple obstacle avoidance techniques or path planning algorithms are commonly used. While effective in controlled settings, they lack the flexibility needed to handle diverse and unpredictable surroundings. In recent years, machine learning (ML) has emerged as a promising alternative. ML allows robots to learn from data and adjust their navigation strategies based on realtime sensory inputs. As a result, this project focuses on implementing ML for robot navigation classification, aiming to create more capable and versatile robotic systems. By utilizing this approach, robots can learn from their experiences and sensory data, improving their ability to navigate complex environments. This adaptive approach is especially valuable in scenarios where the environment undergoes frequent changes or presents diverse and challenging obstacles, beyond what traditional rule-based methods can handle. The utilization of ultrasound sensor data as input provides the robot with valuable distance information, enabling precise obstacle detection and avoidance. Furthermore, incorporating ML into robot navigation enhances their capability to handle complex real-world scenarios and dynamic environments. The use of ultrasound sensor data proves to be a valuable choice, providing crucial information for accurate obstacle detection and path planning. Ultimately, this proposed ML-based approach underscores the potential of ML techniques (i.e., logistic regression, and multilayer perceptron) in enhancing robot navigation capabilities, opening doors for more advanced and autonomous robotic systems capable of operating effectively in diverse and unpredictable environments