Path planning enables Unmanned Aerial Vehicles (UAVs) to generate safe and efficient trajectories toward mission goals, minimizing flight time and energy consumption, while cooperative collision avoidance ensures reliable operation of UAV swarms in dense and dynamic environments. Introducing these two functions together is crucial for enhancing both the autonomy and robustness of UAV systems. This paper presents a novel dynamic path planning and collision avoidance algorithm for multi-UAV systems, known as the Independent Proximal Policy Optimization with Cooperative Collision Avoidance (IPPO-CCA) algorithm. The proposed algorithm integrates Independent Proximal Policy Optimization (IPPO) with Optimal Reciprocal Collision Avoidance (ORCA) and Region-Guided Collision Avoidance (RGCA) to improve navigation efficiency and flight safety in complex environments. Using a shared policy network and a bidirectional gated recurrent unit model, IPPO-CCA enables each UAV to independently learn optimal action strategies, achieving collision-free flight paths and flexible route adjustments. Simulation results across various scenarios confirm that IPPO-CCA significantly improves the overall safety, adaptability, and efficiency of multi-UAV missions. In quantitative terms, IPPO-CCA outperforms MASAC-CCA and MADDPG-CCA in average final reward by 13.66% and 21.70%, respectively. The source code is available at https://github.com/Shihong-Yin/IPPO-CCA.

Sparse time series forecasting (SparseTSF) is a recently proposed lightweight multi-step forecasting model with advantages such as high computational efficiency and wide adaptability. However, the SparseTSF model also has some limitations, for example, it can only downsample a single main period, making it difficult to handle multi-period data. Based on the characteristics of traffic forecasting, this paper integrates weekly and spatial feature extraction modules to extract deep features that fuse daily, weekly, and spatial features. The SparseTSF model is then optimized to construct a multi-period spatial time series forecasting (MSTSF) model. This model is applied to traffic speed forecasting scenarios, aiming to reduce prediction error and achieve a balance between performance and parameter size. Experiments on the Guangzhou traffic and Performance Measurement System (PeMS) datasets show that the MSTSF model performs well in both prediction accuracy and model efficiency. Compared with mainstream deep learning models, this model achieves lower prediction errors. The MSTSF model has advantages such as small parameter size, high iteration efficiency, and fast inference speed, making it suitable for scenarios with limited computational resources. Our model achieves better results in traffic speed forecasting.