The mobile robots work in dynamic settings with variable conditions that can impact their performance. For these robots to be efficient and autonomous, develop a strong path planning and control systems is must to address these issues. Conventional path-planning techniques frequently depend on established algorithms, which could be less adaptable in practical settings. A unique adaptive control technique for improving path planning for autonomous mobile robots is presented in the research. By combining a hybrid bioinspired optimization algorithm with real-time learning capabilities, the suggested method facilitates the robot to adjust to changing environments and maximize its trajectory. In particular, the robot can learn the best routes from human demonstrations in complex surroundings due to the system's use of Learning from Demonstrations (LfD). The research proposed a hybrid approach incorporating the Chaotic Ant-Bat Optimizer (C-ABO) algorithm to improve trajectory reproduction and modify the robot's motion planning. The optimization process improves motion strategies, ensuring precise navigation, enhanced obstacle avoidance, and superior energy efficiency in diverse robotic applications. The proposed method enhances decision-making capabilities and permits the robot to dynamically respond to unexpected environmental changes while maintaining high stability. The performance of the hybrid C-ABO approach is compared on two difficult path planning scenarios with different obstacle densities and terrain complexities using simulations carried out with the Robotics Toolbox based on MATLAB. The results indicate that the hybrid method handles (95.4%) successful progression in obstacle avoidance at (15.2 meters) with a path error of (0.18 meters) and a processing time of (6.5 seconds) in sparse environments. Further, good path planning and adaptive control in dynamic environments have been verified by a real-world test on an indoor nonholonomic mobile robot.
Atham et al. (Fri,) studied this question.