Mobile Robotic Navigation System With Improved Autonomy Under Diverse Scenarios.

Mobile robots integrate a combination of physical robotic elements for locomotion and artificial intelligence algorithms to move and explore the environment. They have the ability to react and make decisions based on the perception they receive from the environment to fulfill the assigned navigation tasks. A crucial issue in mobile robots is to address the energy consumption in the robot design strategy for prolonged autonomous operation. Therefore, the battery charge level is an input variable that is commonly monitored and evaluated at all times, in this type of robots, in order to influence the decision-making with the least user intervention, during the navigation phase. Hence, the robot is capable to complete its tasks successfully. To achieve this, a navigation approach based on a fuzzy Q-Learning architecture for decision-making in combination with a module of artificial potential fields for path planning is introduced. The exhibited behavior of a six-legged robot obtained under this approach, demonstrates the robot’s ability of moving from a starting point to a destination point, considering the need to go to the charging station or to remain static, if necessary.