Reinforcement learning has increasingly showcased its potential in decision-making for the autonomous operation of urban rail transit. However, the inability of reinforcement learning to ensure safety during both the learning and execution phases presents a significant barrier to its practical application. This limitation makes it challenging to implement reinforcement learning in safety-critical domains. In urban rail transit, it is reflected in generating control command sequences that keep the train’s speed consistently below the speed limit. To address this issue, a framework is proposed for intelligent control of autonomous urban rail transit trains, referred to as SSA-DRL (Shield-Searching-Additional-DRL). This framework comprises four modules: a post-posed Shield, a Searching Tree, an Additional Learner, and a DRL framework. It effectively satisfies speed and schedule constraints while optimizing operational processes. The framework is evaluated across sixteen different sections, demonstrating its effectiveness through both basic simulations and additional experiments.

In the digital era, data has become a pivotal asset, advancing technologies such as autonomous driving. Despite this, data trading faces challenges like the absence of robust pricing methods and the lack of trustworthy trading mechanisms. To address these challenges, we introduce a traffic-oriented data trading platform named Data on The Move (DTM), integrating traffic simulation, data trading, and Artificial Intelligent (AI) agents. The DTM platform supports evident-based data value evaluation and AI-based trading mechanisms. Leveraging the common sense capabilities of Large Language Models (LLMs) to assess traffic state and data value, DTM can determine reasonable traffic data pricing through multi-round interaction and simulations. Moreover, DTM provides a pricing method validation by simulating traffic systems, multi-agent interactions, and the heterogeneity and irrational behaviors of individuals in the trading market. Within the DTM platform, entities such as connected vehicles and traffic light controllers could engage in information collecting, data pricing, trading, and decision-making. Simulation results demonstrate that our proposed AI agent-based pricing approach enhances data trading by offering rational prices, as evidenced by the observed improvement in traffic efficiency. This underscores the effectiveness and practical value of DTM, offering new perspectives for the evolution of data markets and smart cities. To the best of our knowledge, this is the first study employing LLMs in data pricing and a pioneering data trading practice in the field of intelligent vehicles and smart cities.

Rational allocation of medical resources can help more people access medical services. To allocate medical resources efficiently and fairly, we need to optimize the layout of healthcare facilities, which helps improve residents' health levels. In this paper, we use the theory of Artificial Scenarios, Computational Experiments, and Parallel Execution (ACP) and Artificial Intelligence (AI) techniques to optimize the health-care facilities' accessibility in a parallel health care system. To illustrate the feasibility of our proposed method, a case study in Gulou, Nanjing, is taken. The results reveal that the existing healthcare facilities are scattered with limited continuity, which fails to meet the demands adequately. With the layout optimization based on the Particle Swarm Optimization (PSO) algorithm, approximately 95 % of residential areas can be covered by adding 15 additional facilities. It not only reduces the standard deviation of accessibility from 0.06 to 0.04 but also significantly improves the fairness and efficiency of healthcare facilities. From an accessibility perspective, optimizing the layout of healthcare facilities ensures fair access to public services and aligns the supply with the demand. The research also provides a reference for the utilization and optimization of public service facilities.

The development of Internet Hospital attracts growing attention worldwide to improve medical service quality and efficiency. However, the existing Internet Hospital failed to fully allocate the patients' consultation demands and improve the level of satisfaction, which is mainly caused by an overlong online waiting time during the diagnostic process. The emergence of Large-Language-Model (LLM) technology provides an opportunity to improve the existing synchronous and sequential online diagnostic process towards an asynchronous and concurrent process. With the consideration of applying LLM technology in developing the Internet Hospital, a conversational-AI-enhanced intelligent diagnostic process framework is proposed in this paper. By hierarchically decomposing the online diagnostic service into three layers, namely the AI doctor, the rotating doctor, and the expert doctor, the diagnostic process is capable of providing instant treatments with a lower misdiagnosis rate, meanwhile relieving the workload of human doctors. In addition, a case study of the Internet Hospital operated by Jiangsu Provincial Hospital is conducted, which reveals the importance of boosting the diagnostic progress by the proposed framework. Further, the proposed framework is examined by a numerical experiment based on statistical data. The experiment results indicate that both the patient waiting time and the misdiagnosis rate can be significantly reduced, which suggests a great potential for applying the proposed framework in practice.

Data trading has been hindered by privacy concerns associated with user-owned data and the infinite reproducibility of data, making it challenging for data owners to retain exclusive rights over their data once it has been disclosed. Traditional data pricing models relied on uniform pricing or subscription-based models. However, with the development of Privacy-Preserving Computing techniques, the market can now protect the privacy and complete transactions using progressively disclosed information, which creates a technical foundation for generating greater social welfare through data usage. In this study, we propose a novel approach to modeling multi-round data trading with progressively disclosed information using a matchmaking-based Markov Decision Process (MDP) and introduce a Social Welfare-optimized Data Pricing Mechanism (SWDPM) to find optimal pricing strategies. To the best of our knowledge, this is the first study to model multi-round data trading with progressively disclosed information. Numerical experiments demonstrate that the SWDPM can increase social welfare 3 times by up to 54 % in trading feasibility, 43 % in trading efficiency, and 25 % in trading fairness by encouraging better matching of demand and price negotiation among traders.

The imbalance between the supply and demand of healthcare resources is a global challenge, which is particularly severe in developing countries. Governments and academic communities have made various efforts to increase healthcare supply and improve resource allocation. However, these efforts often remain passive and inflexible. Alongside these issues, the emergence of the parallel healthcare system has the potential to solve these problems by unlocking the data value. The parallel healthcare system comprises Medicine-Oriented Operating Systems (MOOS), Medicine-Oriented Scenario Engineering (MOSE), and Medicine-Oriented Large Models (MOLMs), which could collect, circulate, and empower data. In this paper, we propose that achieving equilibrium in medical resource allocation is possible through parallel healthcare systems via data empowerment. The supply-demand relationship can be balanced in parallel healthcare systems by (1) increasing the supply provided by digital and robotic doctors in MOOS, (2) identifying individual and potential demands by proactive diagnosis and treatment in MOSE, and (3) improving supply-demand matching using large models in MOLMs. To illustrate the effectiveness of this approach, we present a case study optimizing resource allocation from the perspective of facility accessibility. Results demonstrate that the parallel healthcare system could result in up to 300% improvement in accessibility.

Recent studies have made dozens of attempts to apply multi-agent deep reinforcement learning (MARL) for large-scale traffic signal control. However, most related studies have ignored how to master arterial traffic signal control. We cannot easily extract useful information and search solution space because the arterial traffic control problem has large state-action spaces. Here we tackle these issues by proposing a multi-agent attention-base soft actor-critic (MASAC) model to master arterial traffic control. Specifically, we implement the attention mechanism in the actor and critic network to enhance traffic information extraction ability. More importantly, we are the first to apply the soft actor-critic (SAC) algorithm to train the arterial traffic control model to search more solution spaces. Testing results indicate that the MASAC method significantly outperforms existing MARL algorithms and the multiband-based method. These findings can help researchers to design better model structures for other MARL problems.

In 2014, IEEE Intelligent Transportation Systems Society established a Technical Committee on Transportation 5.0 with the mission of promoting and transforming the deployment of advanced and innovative technologies, especially Artificial Intelligence in transportation. This paper briefly summarizes our main research and findings over the last decade. Transportation Foundation Models, Transportation Scenarios Engineering, and Transportation Operating Systems have been identified as the main directions for the research and development of next-generation intelligent transportation systems.

Rapid development of AI technologies has propelled the seamless integration of physical and cyber worlds with various kinds of online/offline information collected from millions of multimodal sensing systems. The complexity, diversity and uncertainty inherited in such systems, such as Intelligent Transportation Systems (ITSs), have gone far beyond human capacity of managing and controlling. Our team is among the first to propose the idea of utilizing the nearly unlimited computational resources in cyberspace to construct a bottom-up and top-down combined artificial ITSs for testing, experimenting, representation, verification, and validation of physical ITSs. Especially, the parallel transportation has been developed for safer, smarter, greener, and more reliable transportation services. After three decades of research and field studies, the DeCAST in Transverse, i.e., Decentralized/Distributed Autonomous Operations/Organizations (DAO) in transportation systems, has been envisioned. In this paper, we introduce its architecture, operational processes, software and hardware platforms, and real world applications. Specifically, a transportation foundation model driven by artificial transportation systems, parallel learning and federated intelligence, named TengYun, is outlined for DeCAST.

Human and social factors are essential to transportation systems, yet top-down management fails to consider them sufficiently. Consequently, management strategies are not tailored to human needs and are inadequate in providing transportation intelligence. This article investigates a management architecture based on decentralized/distributed autonomous operations/organizations (DAOs) that considers both the technical and societal aspects in our transportation metaverse, TransVerse. This design maps people’s transportation needs in physical space to their digital counterparts in cyberspace, utilizing blockchain technology to guarantee the secure exchange of information and ultimately bring about the Internet of Minds (IoM). With the federated intelligence that emerged in IoM, we can devise reliable and prompt traffic decisions by incorporating consensus, community voting, and smart contracts into the organizational, coordination, and execution structure. Details on operational procedures and key technologies are also covered. To demonstrate the efficacy of DAOs-based management, a case study of world model-driven cooperative signal control is provided, indicating its promising application in future transportation management.

Traffic signal control is shifting from passive control to proactive control, which enables the controller to direct current traffic flow to reach its expected destinations. To this end, an effective prediction model is needed for signal controllers. What to predict, how to predict, and how to leverage the prediction for control policy optimization are critical problems for proactive traffic signal control. In this paper, we use an image that contains vehicle positions to describe intersection traffic states. Then, inspired by a model-based reinforcement learning method, DreamerV2, we introduce a novel learning-based traffic world model. The traffic world model that describes traffic dynamics in image form is used as an abstract alternative to the traffic environment to generate multi-step planning data for control policy optimization. In the execution phase, the optimized traffic controller directly outputs actions in real time based on abstract representations of traffic states, and the world model can also predict the impact of different control behaviors on future traffic conditions. Experimental results indicate that the traffic world model enables the optimized real-time control policy to outperform common baselines, and the model achieves accurate image-based prediction, showing promising applications in futuristic traffic signal control.

Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems. This paper focuses on a novel initialization method for monocular SLAM based on planar features. The algorithm starts by homography estimation in a sliding window. It then proceeds to a global plane optimization (GPO) to obtain camera poses and the plane normal. 3D points can be recovered using planar constraints without triangulation. The proposed method fully exploits the plane information from multiple frames and avoids the ambiguities in homography decomposition. We validate our algorithm on the collected chessboard dataset against baseline implementations and present extensive analysis. Experimental results show that our method outperforms the ne-tuned baselines in both accuracy and real-time.

Traffic flow prediction is one of the most popular topics in the field of the intelligent transportation system due to its importance. Powered by advanced machine learning techniques, especially the deep learning method, prediction accuracy noticeably increases in recent years. However, most existing methods applied a data-driven paradigm and tend to ignore the outliers, which result in poor performance while handling burst phenomena in the traffic system. To overcome this problem, the prediction model needs to recognize different patterns and handle them in different ways. In this paper, we propose a new prediction model (called pattern sensitive network) that can handle different traffic patterns automatically. By using adversarial training, our model can make more accurate predictions in unusual states without compromising its performance in usual states. Experiments demonstrate that our method can work well in both usual traffic states and unusual traffic states.

In this paper, we propose a deep neural network-based car-following model that has two distinctive properties. First, unlike most existing car-following models that take only the instantaneous velocity, velocity difference, and position difference as inputs, this new model takes the velocities, velocity differences, and position differences that were observed in the last few time intervals as inputs. That is, we assume that drivers’ actions are temporally dependent in this model and try to embed prediction capability or memory effect of human drivers in a natural and efficient way. Second, this car-following model is built in a data-driven way, in which we reduce human interference to the minimum degree. Specially, we use recently developing deep neural networks rather than conventional neural networks to establish the model, since deep learning technique provides us more flexibility and accuracy to describe complicated human actions. Tests on empirical trajectory records show that this deep neural network-based car-following model yield significantly higher simulation accuracy than existing car-following models. All these findings provide a novel way to study traffic flow theory and traffic simulations.

Parking is one basic function of autonomous vehicles. However, parking still remains difficult to be implemented, since it requires to generate a relatively long-term series of actions to reach a certain objective under complicated constraints. One recently proposed method used deep neural networks(DNN) to learn the relationship between the actual parking trajectories and the corresponding steering actions, so as to find the best parking trajectory via direct recalling. However, this method can only handle a special vehicle whose dynamic parameters are well known. In this paper, we use transfer learning technique to further extend this direct trajectory planning method and master general parking skills. We aim to mimic how human drivers make parking by using a specially designed deep neural network. The first few layers of this DNN contain the general parking trajectory planning knowledge for all kinds of vehicles; while the last few layers of this DNN can be quickly tuned to adapt various kinds of vehicles. Numerical tests show that, combining transfer learning and direct trajectory planning solution, our new approach enables automated vehicles to convey the knowledge of trajectory planning from one vehicle to another with a few try-and-tests.