Application of reinforcement learning algorithm on robot motion control and navigation in webots simulator

Covid-19 has changed people’s way of life since its outbreak in December 2019. The transmission of the virus mainly relies on droplets or aerosols produced by infected people while they breathe, talk, cough or sneeze. The infection can occur over a long distance, especially indoors. To reduce connectivity between the people indoors such as in restaurants, the application of robots for food delivery may be one of the solutions. In this research, a reinforcement learning algorithm is applied to the motion control and navigation of a robot which can be modified into a robot food runner to maintain social distances in restaurants. In this project, we test the algorithm’s ability to explore the environment and find a suitable path to the target point through learning by comparing its trajectories to the shortest theoretical path. The results obtained through the simulation on Webots show that the algorithm works well to find a destination from a randomly selected starting point even though a random obstacle is presented. However, still it has great potential to be extended to a continuous environment.