Search

Robot navigation involves a challenging task: path planning for a mobile robot operating in a changing environment. This work presents an enhanced Q-learning based path planning technique. For mobile robots operating in dynamic environments, an algorithm and a few heuristic searching techniques are suggested. Enhanced Q-learning employs a novel exploration approach that blends Boltzmann and ε-greedy exploration. Heuristic searching techniques are also offered in order to constrict the orientation angle variation range and narrow the search space. In the meantime, the robotics literature of the energy field notes that the decrease in orientation angle and path length is significant. A dynamic reward is suggested to help the mobile robot approach the target location in order to expedite the convergence of the Q-learning and shorten the computation time. There are two sections to the experiments: quick and reassured route planning. With quickly path planning, the mobile robot can reach the objective with the best path length, and with secure path planning, it can avoid obstacles. The superior performance of the suggested strategy is quick and reassured 8-connection Q-learning (Q8CQL) was validated by simulations, comparing it to classical Q-learning and other planning methods in terms of time taken and ideal path.

In engineering, the use of mobile robots to teach automatic control is becoming more common because of the interesting experiments that can be conducted with them. In this paper, a mobile robot that applies reinforcement learning in different scenarios is shown, to get rewards, the agent learns by acting in the environment. creating a balance between new information and our current understanding of the environment. In this way, the algorithm can be divided into two stages: the learning stage and the operational stage. In the first phase, the robot learns how to go from where it is to a known destination, it builds a learning matrix that is subsequently utilized during the operational stage using the rewards and environment data. In this paper, the algorithm was studied in terms of rapid learning for the mobile robot and reducing the process of repetition in learning by specifying the values of alpha (α) and gamma (γ) in a way that is appropriate for preserving the variance and differentiation between them. To evaluate the robot’s adaptability to various dynamic situations, several simulated test scenarios were executed. In the testing situations, several target motion kinds and numbers of obstacles with various dynamicity patterns were used. The test scenarios illustrated the robot’s adaptability to various settings.