Damaged sensor data, often caused by noise interference and data loss, impairs the decision-making accuracy of Deep Reinforcement Learning (DRL) traffic signal control models. This paper takes RobustLight (ICML 2025) as the core case and analyzes it from a data science perspective. We introduce DRL-based traffic signal control and diffusion model principles, then examine RobustLight's dual-process framework, DSI algorithm, Denoise and Repaint modules, and its non-Markov loss design. Experiments on Jinan, Hangzhou and New York datasets under four adversarial attacks and sensor damage show that RobustLight achieves up to 50.43% improvement in state recovery, with ATT reduced by up to 42%. Finally, we discuss real-world challenges including anomaly-detection dependency, inference latency, and cross-domain generalization.

Show more

Convolutional Neural Networks (CNN) are not widely used in high-risk decision-making because they have black-box nature. This paper investigates three visualization methods, Gradient-weighted class activation mapping (Grad-CAM), Score-weighted visual explanations for convolutional neural networks (Score-CAM), and Local interpretable model-agnostic explanations (LIME), across classification, detection, and medical imaging tasks. Theoretically, Grad-CAM relies on gradient backpropagation to weight feature maps. This offers computational efficiency but suffers from gradient instability and coarse spatial resolution. Score-CAM replaces gradients with forward pass confidence scores. This enhances robustness and spatial alignment at the cost of linearly increasing inference overhead. LIME is a model agnostic surrogate. It provides flexible local explanations but is inherently sensitive to perturbation sampling and hyperparameter choices, leading to poor reproducibility. Grad-CAM performs best in dermatologist agreement and localization accuracy. Score-CAM show superior spatial alignment in pneumonia detection with gradient free robustness. LIME shows flexibility but suffers from instability and hyperparameter sensitivity. The differences are obvious: Grad-CAM is good at interpretability, Score-CAM is good at robustness with computational cost, and LIME is good at model agnostic applicability. Based on these differences, these three visualization tools can be selected for real-world tasks.

Show more

Robotic laparoscopic surgery is moving from conventional teleoperation toward greater autonomy. Previous studies usually only examined individual parts of this transition. The technologies enabling autonomous laparoscopic surgery are less often discussed as one integrated system. This review examines the system through three components: hardware infrastructure, environmental perception, and decision-making. The hardware discussion covers instrument actuation, vision and force sensing, and various robotic platforms. The perception section follows proprioceptive, visual and force data as they are converted into a unified representation of the surgical state. It focuses on 3D scene reconstruction, instrument segmentation, workflow recognition, and multimodal fusion. The decision and control section discusses classical control and data-driven methods, especially the hierarchical imitation learning and reinforcement learning for long-horizon surgical tasks. The review concludes with the main barriers to clinical translation, including the sim-to-real gap, deformable tissue modeling, and safety and regulatory requirements. These areas together show how embodied intelligence may influence future autonomous surgery in the operating room.

Show more

Supercapacitors, combining high power density and long cycle lifetime, have attracted great attention in recent years. Particularly for applications that require both energy and fast power response, such as frequency regulation in power systems, rail transit, and high-power pulse application, supercapacitors are promising candidate energy storages. Transition metal oxides, with their high theoretical specific capacitance, are the most widely studied pseudocapacitive materials for SCs. Three most studied metal-oxide electrode materials including RuO 2 , MnO 2 , and NiCo 2 O 4 are introduced. Despite RuO 2 is always treated as the benchmark material with metal-level conductivity, it is unfortunately expensive and rare. MnO 2 , however, is environmentally friendly and relatively cheap, yet suffers from poor conductivity and Mn dissolution problem. NiCo 2 O 4 with relatively excellent conductivity among transition metal oxides exhibits special pseudocapacitive behaviors under certain nanostructures and test conditions. The above three materials manifest the trade-off among cost, electrical conductivity, cycling stability, and high mass loading performance, and none of them shows overwhelming advantages in all items. Similar problems, poor conductivity, insufficient cycling stability, and poor high mass loading performance have been shared by metal-oxide electrode materials. Constructing conductive network has become a commonly used method to improve the performance of metal-oxide electrodes. Constructing porous structures is also a widely used approach to overcome the above challenges in metal oxides. A qualitative comparison of the three materials is also provided. Finally, future work should continue to improve conductivity, enhance cycling stability, and maintain fast charge transport at commercially relevant electrode loadings.

Show more