Path planning and control for mobile robots using machine learning

As the demands of autonomous mobile robots are increasing in recent years, the requirement of the path planning/navigation algorithm should not be content with the ability to reach the target without any collisions, but also should try to achieve possible optimal or suboptimal path from the initial position to the target according to the robot's constrains in practice. This thesis investigates path planning and control strategies for mobile robots with machine learning techniques, including ground mobile robots and flying UAVs. In this thesis, the hybrid reactive collision-free navigation problem under an unknown static environment is investigated firstly. By combining both the reactive navigation and Q-learning method, we intend to keep the good characteristics of reactive navigation algorithm and Q-learning and overcome the shortcomings of only relying on one of them. The proposed method is then extended into 3D environments. The performance of the mentioned strategies are verified by extensive computer simulations, and good results are obtained. Furthermore, the more challenging dynamic environment situation is taken into our consideration. We tackled this problem by developing a new path planning method that utilizes the integrated environment representation and reinforcement learning. Our novel approach enables to find the optimal path to the target efficiently and avoid collisions in a cluttered environment with steady and moving obstacles. The performance of these methods is compared with other different aspects. In addition, another important navigation problem, reconnaissance and surveillance problem for UAVs, is studied and two algorithms are presented. It requires drones to fully cover the area of interest along their trajectories. In the first method, a two-phase strategy is presented and enables to operate with a given altitude. Furthermore, an occlusion-aware UAV reconnaissance and surveillance approach is developed, which takes both UAV kinematics constraints and camera sensing limitations into consideration. We have implemented all the proposed algorithms by illustrative computer simulations in different scenarios, and the results have confirmed the effectiveness of these approaches. An extra study on the steering angle prediction algorithm for autonomous vehicles is presented. The proposed algorithm employs the convolutional neural network to extract features from the human driver and predicts the steering angle for autonomous driving. The performance of the algorithm is validated through simulations in different scenarios, we find the learned features can be transferred to the environment that has never been seen before