Dynamic production and service scheduling are critical in manufacturing servitization. Unlike previous research assuming unrealistic specific mappings between products and services, this paper studies a more general and complex setting with a two-product-two-service mapping in a product service system, formulating it as a Markov Decision Process model. To solve this model with large-scale cases, designing a data-driven prediction algorithm is a common approach to overcome the curse of dimensionality. However, there might exist inconsistencies in the statistical distribution between the training and testing sets, as the training samples generated by the exact algorithm may not cover the entire state space. To tackle this problem, we propose a novel model-and-data-driven framework. We extract a service priority rule from the model as prior knowledge and embed it into the machine learning algorithm through tailored feature engineering. This strengthens prediction capabilities in unexplored state space regions compared to a purely data-driven approach. Numerical experiments validate our contributions, displaying the potential for embracing industrial automation and exploring the synergy effects for further exploration of the optimal structure as more effective prior knowledge. Note to Practitioners—Dynamic joint scheduling of production and service plays an important role in industrial automation. In this context, a wide range of studies are dedicated to developing efficient algorithms to meet the quick response requirement to tackle large-scale cases beyond the capability of exact algorithms. However, these studies often rely on unrealistic assumptions or have unsatisfactory computational performance, limiting potential cost reduction. To overcome this challenge, we relax unnecessary hypotheses and generalize the problem by allowing for a more generalized production-service mapping, which better reflects the reality. Apart from that, we integrate the prior knowledge into existing data to construct a more powerful approximation algorithm and enrich the prediction capability to accommodate the dynamic environment. With greater computation resources and data samples, the proposed algorithm achieves superior solutions. Furthermore, our research uncovers some key properties of the product service system, which could be leveraged to customize more effective automated scheduling rules.

Traditional roadway safety assessment heavily relies on historical crash data, overlooking real-time factors such as driver behaviors and current traffic conditions and lacking forward-looking analysis for predicting future trends. This study introduces an enhanced innovative data fusion method based on the safe route mapping (SRM) methodology with combined use of historical crash data and real-time data, leveraging a custom-built Android app to amalgamate road and vehicle data effectively, showcasing notable advancements in real-time risk assessment. The enhanced safe route mapping (ESRM) framework monitors driver actions and road conditions meticulously. Data collected from drivers is analyzed on a central server using facial recognition algorithm to detect signs of fatigue and distractions, assessing overall driving competence. Simultaneously, roadside cameras capture live traffic data, analyzed using a specialized video analytics method to track vehicle speed and paths. The fusion of these data streams enables the introduction of a predictive model, Light gradient boosting machine (GBM), forecasting potential immediate issues for drivers. Predicted risk scores are integrated with historical crash data using a Fuzzy logic model, delineating risk levels for different road sections. The performance of ESRM model is tested using real-world data and a driving simulation, demonstrating remarkable accuracy, especially in accounting for real-time fusion of driver behavior and traffic conditions. The resultant visual risk heatmap aids authorities in identifying safer routes, proactive law enforcement deployment, and informed trip planning based on real-time risk levels. This study not only underscores the importance of real-time data in roadway safety but also paves the way for data-driven, dynamic risk assessment models, potentially reducing road accidents and fostering a safer driving environment.

Multiple-view stereo has potential applications in robotic operations and autonomous driving (unstructured environment construction, visual servo). With assisted depth information, inertial navigation systems can achieve precise navigation. It is, especially suitable for GPS failures in complex environments. Accurate depth estimation is a challenge in low-textured or occluded regions. To alleviate the inference of incorrect depth, a multi-stage pixel-visibility learning-based stereo network is presented in this paper. Its improvements are as follows: 1) a new content-adaptive cost volume aggregation mechanism based on neighboring pixel-wise visibility is designed to effectively produce more accurate and smoother depth map predictions in the object boundary. 2) global convolution block and boundary refinement block are developed to regularize its cost volume, they can learn the inherent constraints of feature matching correspondence and effectively mitigate the depth estimation uncertainty in low-textured regions. 3) a new loss function is designed to measure the uncertainty of predicted probability distribution and enhance the reliability of depth map inference. Experimental results on the indoor DTU datasets and the outdoor Tanks & Temples datasets indicate that our method can achieve superior performance and has a powerful generalization ability, which is comparable to state-of-the-art works. Note to Practitioners—Multiple-view stereo (MVS) can estimate dense 3D representations of scenes, which is widely used in autonomous driving, robotic navigation, virtual reality (VR), and augmented reality (AR). Aiming at the problem of incorrect depth inference in low-textured or occluded regions, this work proposes a novel multi-stage depth prediction method based on neighboring pixel-wise visibility. Our method cannot only achieve accurate depth estimation for robot perception but also make no concession to real-time performance. It is clear that the proposed method has good potential in 3D reconstruction, robotic navigation, and VR/AR fields to provide accurate depth estimation in real-time with limited memory consumption.

With the emerging connected-vehicle technologies and smart roadways, the need for intelligent adaptive traffic signal controls (ATSC) is more than ever before. This paper first proposes an Accumulated Exponentially Weighted Waiting Time-based Adaptive Traffic Signal Control (AEWWT-ATSC) model to calculate priorities of roadways for signal scheduling. As the size of the traffic network grows, it adds great complexities and challenges to computational efficiencies. Considering this, we propose a novel Distributed Multi-agent Reinforcement Learning (DMARL) with a graph decomposition approach for large-scale ATSC problems. The decomposition clusters intersections by the level of connectivity (LoC), defined by the average residual capacities (ARC) between connected intersections, enabling us to train subgraphs instead of the entire network in a synchronized way. The problem is formulated as a Markov Decision Process (MDP), and the Double Dueling Deep Q Network with Prioritized Experience Replay is utilized to solve it. Under the optimal policy, the agents can select the optimal signal durations to minimize the waiting time and queue size. In evaluation, we show the superiority of the AEWWT-ATSC based RL methods in different densities and demonstrate the DMARL with a graph decomposition approach on a large graph in Manhattan, NYC. The approach is generic and can be extended to various types of use cases.

The use of systematic techniques with historical crash data and qualitative measures has long been a common practice to identify the problematic road features and develop countermeasures to mitigate the crash risk in crash-prone locations. This paper proposes a novel approach,Safe Route Mapping(SRM) model that integrates crash-based estimates with conflict risks computed from driver-based data to score the safety of roadways. An advanced Safety Performance Function (SPF) estimates the number of crashes, and a driver-based model computes dynamic conflict risk measures from driver and traffic data. In real-life implementations of the proposed methodology, the driver-based data and traffic data can be collected from vehicles or infrastructure-based data sources, including smartphones. We demonstrate the methodology using real historical crash data and simulated driver-based data obtained from VISSIM and SSAM. We show safety risk heat maps for the example roadway and illustrate how these maps change with driver types and traffic volumes. The proposed methodology fills the existing gaps in the use of near real-time dynamic data to designate safe corridors, dispatch law enforcement, and plan safety projects. Drivers can also use the road heat maps for situational awareness and trip planning.

Traffic congestion is an inescapable problem that frustrates drivers in megacities. Although there is hardly a way to eliminate the congestion, it is possible to mitigate the impact through predictive methods. This paper develops a data-driven optimization approach for the dynamic shortest path problems (DSPP), considering traffic safety for urban navigations. The dynamic risk scores and travel times at different times and locations are estimated by the Safe Route Mapping (SRM) methodology and Long Short-Term Memory (LSTM) with Autoencoder, respectively, where possible variations in the future are considered. The DSPP is formulated as a mixed-integer linear programming problem under risk constraints to minimize the total travel cost, defined as the weighted sum of distance and travel time. To improve the efficiency of the DSPP, we design an improved tabu search with alternative initial-solution algorithms to accommodate various problem scales. Moreover, subgraph and self-adaptive insertion techniques are adopted as acceleration strategies to enhance computational efficiency further. Numerical experiments investigate the computational performance and the solution quality of our algorithm. The result shows satisfactory solution quality and computational efficiency with the proposed acceleration strategies compared to the CPLEX solver, a label-setting algorithm, and a state-of-the-art algorithm. Our algorithm can also compete with Google Maps regarding the travel cost in a real network in Manhattan, NY, USA, which is promising for Urban Navigations.