Path Planning for Unmanned Surface Vehicles with Strong Generalization Ability Based on Improved Proximal Policy Optimization.

To solve the problems of path planning and dynamic obstacle avoidance for an unmanned surface vehicle (USV) in a locally observable non-dynamic ocean environment, a visual perception and decision-making method based on deep reinforcement learning is proposed. This method replaces the full connection layer in the Proximal Policy Optimization (PPO) neural network structure with a convolutional neural network (CNN). In this way, the degree of memorization and forgetting of sample information is controlled. Moreover, this method accumulates reward models faster by preferentially learning samples with high reward values. From the USV-centered radar perception input of the local environment, the output of the action is realized through an end-to-end learning model, and the environment perception and decision are formed as a closed loop. Thus, the proposed algorithm has good adaptability in different marine environments. The simulation results show that, compared with the PPO algorithm, Soft Actor-Critic (SAC) algorithm, and Deep Q Network (DQN) algorithm, the proposed algorithm can accelerate the model convergence speed and improve the path planning performances in partly or fully unknown ocean fields.

Exploring air pollution characteristics from spatio-temporal perspective: A case study of the top 10 urban agglomerations in China.

Air pollution has become a global public health risk factor as rapid urbanization advances. To observe the air pollution situation, air monitoring stations have been established in many cities, which record six air pollutants. Previous studies have identified cities exhibiting similar air pollution characteristics by combining principal component analysis (PCA) with cluster analysis (CA). However, spatial and temporal effects were neglected. In this paper, we focus on the combination of GTWPCA and STCA, which fully incorporates spatio-temporal effects. It is then applied to air pollution data from the top 10 urban agglomerations in China during 2016-2021. Key experimental findings include: 1. GTWPCA provides a more detailed interpretation of local variation than PCA. 2. Compared with CA, STCA highlights the coupling effect in the spatial and temporal dimensions. 3. The combination of GTWPCA and STCA captures similar air pollution characteristics from spatio-temporal perspectives, which has the potential to help environmental authorities take further action to control air pollution.