Due to the complexity of interactive environments, dynamic obstacle avoidance path planning poses a significant challenge to agent mobility. Dynamic path planning is a complex multi-constraint combinatorial optimization problem. Some existing algorithms easily fall into local optimization when solving such problems, leading to defects in convergence speed and accuracy. Reinforcement learning has certain advantages in solving decision sequence problems in complex environments. A Q-learning algorithm is a reinforcement learning method. In order to improve the value evaluation of the algorithm in solving practical problems, this paper introduces the priority weight into the Q-learning algorithm. The improved algorithm is compared with existing algorithms and applied to dynamic obstacle avoidance path planning. Experiments show that the improved algorithm dramatically improves the convergence speed and accuracy and increases the value evaluation. The improved algorithm finds the shortest path of 16 units in 27 seconds.

No abstract

No abstract

The avoidance of collisions among ships requires addressing various factors such as perception, decision-making, and control. These factors pose many challenges for autonomous collision avoidance. Traditional collision avoidance methods have encountered significant difficulties when used in autonomous collision avoidance. They are challenged to cope with the changing environment and harsh motion constraints. In the actual navigation of ships, it is necessary to carry out decision-making and control under the constraints of ship manipulation and risk. From the implementation process perspective, it is a typical sequential anthropomorphic decision-making problem. In order to solve the sequential decision problem, this paper improves DQN by setting a priority for sample collection and adopting non-uniform sampling, and it is applied to realize the intelligent collision avoidance of ships. It also verifies the performance of the algorithm in the simulation environment.