The analysis and prediction of agent trajectories are crucial for decision-making processes in intelligent systems, with precise short-term trajectory forecasting being highly significant across a range of applications. Agents and their social interactions have been quantified and modeled by researchers from various perspectives; however, substantial limitations exist in the current work due to the inherent high uncertainty of agent intentions and the complex higherorder influences among neighboring groups. SocialMOIF is proposed to tackle these challenges, concentrating on the higher-order intention interactions among neighboring groups while reinforcing the primary role of first-order intention interactions between neighbors and the target agent. This method develops a multi-order intention fusion model to achieve a more comprehensive understanding of both direct and indirect intention information. Within SocialMOIF, a trajectory distribution approximator is designed to guide the trajectories toward values that align more closely with the actual data, thereby enhancing model interpretability. Furthermore, a global trajectory optimizer is introduced to enable more accurate and efficient parallel predictions. By incorporating a novel loss function that accounts for distance and direction during training, experimental results demonstrate that the model outperforms previous state-of-the-art baselines across multiple metrics in both dynamic and static datasets.

The wind energy, as a kind of renewable energy resources, has the potential to replace traditional fossil fuels. However, its intermittent power output can incur frequency instability due to the instantaneous unbalance between power generation and load demand. To smooth the penetration of wind energy, this paper presents a robust cooperative load frequency control (LFC) strategy for multi-area power systems, which is a hierarchical control approach. For the low-level wind turbine control, this paper adopts model predictive control (MPC) method to achieve the rated wind power tracking. In the meantime, an improved event-triggered scheme (ETS) considering multiple historic released signals is employed to relieve the computational burden of MPC. For the high-level cooperative LFC, this paper incorporates the robust performance index in the control synthesis to suppress the impact of intermittent wind power on frequency stability. In addition, to address the underlying shift of the steady-state operating point caused by the intermittent wind power supply, this paper improves the commonly used small-signal LFC model by adding an uncertain matrix, which reasonably explains the possible change of system parameters and extends the applicability of the traditional LFC model. Simulations are done on a four-area power system, and the results verify the efficacy of the presented event-triggered scheme and the robust cooperative LFC approach.Note to Practitioners—To promote the penetration of wind energy into power systems, this work explores a robust cooperative LFC approach under multi-agent structure to ensure the stability of the system, aiming at extending the applicability of existing approaches. The proposed approach is hierarchical. At the rated wind power tracking level, the MPC is employed to handle constraints associated with actuating devices, such as heterogeneous convertors. Simultaneously, an improved ETS considering multiple historic triggered signals is integrated in the MPC to reduce the computational burden. At the power system level, the robust performance index is incorporated in the control design to smooth the impacts of intermittent wind power on frequency stability. Additionally, the study accounts for the potential shift of the steady-state operating point and improves the traditional small-signal LFC model by adding an uncertain matrix, which can better explain the variation of system parameters and is more applicable in practical power system engineering. Simulation results demonstrate that the proposed robust cooperative LFC approach can effectively maintain the system frequency within the admissible range under the high penetration of wind energy, whereas the traditional PI controller falls short in this regard.

Pedestrian trajectory prediction is crucial for intelligent surveillance, social robot navigation, and autonomous driving systems, attracting substantial research attention in recent years. Despite significant advances, accurate trajectory prediction remains challenging due to the inherent uncertainty in pedestrian intentions and the multimodal nature of human movement patterns. There remain two limitations in existing methods. First, they focus solely on predicting final goals while overlooking crucial intermediate intentions that guide pedestrian movement. Second, they utilize a static latent distribution model across all future timesteps, which fails to capture the dynamic and evolving nature of trajectory uncertainties as pedestrians move. To address these challenges, we propose a novel timewise intentions and time-varying distribution network, TITDNet, which can estimate pedestrian intentions over time while dynamically modeling trajectory uncertainties at each future timestep. Specifically, TITDNet includes two key components: an intention generator that estimates dynamic pedestrian intentions, and a variational autoencoder that captures the time-varying multimodal nature of future trajectories. A trajectory decoder then integrates historical movement patterns, predicted intentions, and learned distributions to generate accurate future trajectories. Extensive experiments on ETH, UCY, and SDD benchmark datasets demonstrate that our approach significantly outperforms the state-of-the-art methods.

Self-supervised monocular depth estimation usually assumes that training samples contain only static objects, which leads to poor performance in real-world environments. The presence of dynamic objects incurs camera motion estimation errors, motion blur, and occlusions, which induce significant challenges for network training. To address these issues, we introduce EDS-Depth, a self-supervised learning framework, that improves monocular depth estimation in dynamic scenes. Firstly, we propose a novel TCE (Temporal Continuity Enhancement) strategy to reduce camera motion estimation errors and motion blur caused by dynamic objects. Video frames are interpolated to generate more continuous frames in order to smooth dynamic changes and enrich motion details. Secondly, we design a novel IPDM (Iterative Pseudo Depth Masking) module to address inaccurate object motion and occlusions in dynamic scenes. The module integrates multiple optical flows from different frames for triangulation, generating optimal depth as pseudo-supervision labels in dynamic regions. Extensive experiments on Cityscapes and KITTI datasets demonstrate the effectiveness of EDS-Depth, which surpasses state-of-the-art self-supervised monocular depth estimation methods, particularly in dynamic scenes.

The microgrid, capable of providing flexible and controllable means to integrate distributed renewable energy sources (DRESs), has long been seen as a most promising solution to convert DRESs into the electrical power. However, the intermittent power output of DRESs, together with the unexpected load perturbations, challenges the frequency stability of microgrids. In this context, the work proposes a robust distributed load frequency control (DLFC) method for multi-area wind energy-dominated microgrids, in which way all interconnected areas can work cooperatively to confront the unbalanced power occurring in partial areas. Considering the flexibility for large-scale deployment, the wind energy is taken as the DRES, while the thermal power plant is chosen as the base power generation. To mitigate the fluctuation of wind power output caused by uncertain wind speed, a sample-based stochastic model predictive control approach is presented. For the high-level DLFC of multi-area microgrids, robust performance index is incorporated in stability analysis and control synthesis. Moreover, temporary phasor measurement unit (PMU) failures are considered in DLFC design and are modeled by random Bernoulli variables to quantitatively analyze their impacts on frequency dynamics. Validations on a four-area microgrid verify the efficacy of the proposed robust DLFC method under different PMU failure probabilities.

Pedestrian trajectory prediction has been broadly applied in video surveillance and autonomous driving. Most of the current trajectory prediction approaches are committed to improving the prediction accuracy. However, these works remain drawbacks in several aspects, complex interaction modeling among pedestrians, the interactions between pedestrians and environment and the multimodality of pedestrian trajectories. To address the above issues, we propose one new trajectory distribution aware graph convolutional network to improve trajectory prediction performance. First, we propose a novel directed graph and combine multi-head self-attention and graph convolution to capture the spatial interactions. Then, to capture the interactions between pedestrian and environment, we construct a trajectory heatmap, which can reflect the walkable area of the scene and the motion trends of the pedestrian in the scene. Besides, we devise one trajectory distribution-aware module to perceive the distribution information of pedestrian trajectory, aiming at providing rich trajectory information for multi-modal trajectory prediction. Experimental results validate the proposed model can achieve superior trajectory prediction accuracy on the ETH & UCY, SSD, and NBA datasets in terms of both the final displacement error and average displacement error metrics.