Learning procedural-aware video representations is a key step towards building agents that can reason about and execute complex tasks. Existing methods typically address this problem by aligning visual content with textual descriptions at the task and step levels to inject procedural semantics into video representations. However, due to their high level of abstraction, "task" and "step" descriptions fail to form a robust alignment with the concrete, observable details in visual data. To address this, we introduce "states", i.e., textual snapshots of object configurations, as a visually-grounded semantic layer that anchors abstract procedures to what a model can actually see. We formalize this insight in a novel Task-Step-State (TSS) framework, where tasks are achieved via steps that drive transitions between observable states. To enforce this structure, we propose a progressive pre-training strategy that unfolds the TSS hierarchy, forcing the model to first ground representations in states before associating them with steps and, ultimately, high-level tasks. Extensive experiments on the COIN and CrossTask datasets show that our method outperforms baseline models on multiple downstream tasks, including task recognition, step recognition, and next step prediction. Ablation studies show that introducing state supervision is a key driver of performance gains across all tasks. Additionally, our progressive pretraining strategy proves more effective than standard joint training, as it better enforces the intended hierarchical structure.

Flow, a state of complete immersion, focus, and enjoyment, has important implications for learning, productivity, and well-being. While research on flow is growing, there remains a need for refined methods to elicit and assess flow states specifically in immersive VR environments. In this work, we address this need by developingBeat Flow, a VR music rhythm game tailored to participants' skill levels, designed to evoke distinct flow states. Instead of using traditional physiological apparatus that limits mobility, we employ lightweight wearable devices to capture electroencephalogram (EEG), galvanic skin response (GSR), photoplethysmography (PPG), and eye blink. Furthermore, we propose a VR-native self-report tool, the 3D Flow Scale (3FS), for efficient flow assessment in VR environments. Besides, we develop a deep learning model with a self-supervised pre-training strategy to classify flow states, achieving 78.4% accuracy within a 10-second time window using 5-fold cross-validation. The model demonstrates state-of-the-art performance, especially in cross-user scenarios, advancing flow detection in VR and paving the way for flow-aware VR applications across various domains.

Sensor faults and actuator faults inevitably exist in DC microgrids due to device aging, environmental changes, or cyber-attacks, which seriously degrades control performance. The existing resilient control methods for DC microgrids still bear some deficiencies, such as poor performance, limited applicability, and heavy tasks of calculation or communication. To overcome these problems and to realize the resilient control for DC microgrids with both sensor faults and actuator faults, this article has proposed a decentralized control scheme to guarantee the control resilience of bus voltage regulation and current sharing simultaneously. The proposed scheme contains a residual-based fault detection logic to locate the faulty sensor, an adaptive fault estimation observer to estimate the system state and faults simultaneously, and a finite-time fault-tolerant control law to guarantee resilience to faults. The stability proof based on Lyapunov analysis is given to validate the effectiveness of the proposed scheme. Finally, a DC microgrid model is built in the hardware-in-the-loop testbed to validate the effectiveness and superiority of the proposed decentralized resilient control scheme.

Distributed control is widely applied in DC microgrids (MGs) for the cooperation of multiple distributed generations (DGs), but the inevitable communication delays between controllers will deteriorate the control performance including the steady-state and stability. In this paper, a unified distributed control approach based on PI consensus algorithm is proposed to achieve accurate weighted average voltage recovery and current proportional sharing with communication delays. Meanwhile, the scattering transformation is introduced to compensate for the adverse effect of heterogeneous communication delays on stability. It is proven that the DC MG is guaranteed to be stable with unbounded and heterogeneous communication delays by the Lyapunov stability criterion. Finally, the effectiveness and advantages of the proposed distributed control are verified via MATLAB/Simulink.

This paper investigates the resilient consensus control problems for distributed energy storage (DES) systems in DC microgrids (MGs) with false data injection attacks (FDIAs) in the communication channels. The existing resilient control methods still bear some deficiencies, such as poor performance, limited applicability, and heavy calculation. To overcome these problems and to realize the resilient control of bus voltage regulation and state of charge (SoC) balancing for DES systems in DC MG, this article has proposed a resilient consensus control scheme to guarantee resilience under unbounded FDIAs. The proposed scheme uses input-output feedback linearization to construct a second-order linear system for each DES node and utilizes the dual-layer communication architecture to establish the resilient observer. Compared with other model-based resilient control methods, the proposed scheme can effectively deal with unbounded FDIAs with lower costs in both communication and calculation. Then, the stability analysis based on the Lyapunov technique is given to prove the feasibility of the proposed scheme. Finally, the DC MG test model is built in MATLAB/Simulink to verify the efficiency of the proposed scheme.