Abstract:The transportation system of those countries has a huge traffic flow is bearing great pressure on transportation planning and management. Vehicle path planning is one of the effective ways to alleviate such pressure. Deep reinforcement learning (DRL), as a state-of-the-art solution method in vehicle path planning, can better balance the ability and complexity of the algorithm to reflect the real situation. However, DRL has its own disadvantages of higher search cost and earlier convergence to the local optimum… Show more
“…Moreover, the model has assigned different memory weights to different memory-forgetting durations based on human memory characteristics [67]. Nai et al have proposed a hybrid policy gradient-based actor-critic generative adversarial RL model to describe the route choice strategies and optimization methods for micro travelers [68]. Zhao et al have proposed a universal deep inverse reinforcement learning (IRL) framework for link-based route choice modeling, which combines different features of state, action, and travel context and captures the dynamic properties of micro route choice, achieving competitive interpretability of micro travel decision-making [69].…”
Section: Models With Information Factors Consideredmentioning
Urban day-to-day travel systems generally exist in various types of cities. Their modeling is difficult due to the uncertainty of individual travelers in micro travel decision-making. Moreover, with the advent of the information age, intelligent connected vehicles, smartphones, and other types of intelligent terminals have placed urban day-to-day travel systems in an information environment. In such an environment, the travel decision-making processes of travelers are significantly affected, making it even more difficult to give theoretical explanations for urban day-to-day travel systems. Considering that analyzing urban day-to-day travel patterns in an information environment is of great significance for governing the constantly developing and changing urban travel system and, thus, of great importance for the sustainable development of cities, this paper gives a systematic review of the theoretical research on urban day-to-day travel and its development in an information environment over the past few decades. More specifically, the basic explanation of an information environment for urban day-to-day travel is given first; subsequently, the theoretical development of micro decision-making related to individual day-to-day travelers in an information environment is discussed, and the theoretical development related to changes in urban macro traffic flow, which can be recognized as the aggregation effect formed by individual micro decision-making, is also discussed; in addition, the development of understanding different types of traffic information that travelers may obtain in an information environment is discussed; finally, some important open issues related to the deep impact of information environment on urban day-to-day travel systems that require further research are presented. These valuable research directions include using information methods to fit day-to-day travel patterns of cities and implementing macro and micro integrated modeling for urban day-to-day travel systems based on complex system dynamics and even quantum mechanics.
“…Moreover, the model has assigned different memory weights to different memory-forgetting durations based on human memory characteristics [67]. Nai et al have proposed a hybrid policy gradient-based actor-critic generative adversarial RL model to describe the route choice strategies and optimization methods for micro travelers [68]. Zhao et al have proposed a universal deep inverse reinforcement learning (IRL) framework for link-based route choice modeling, which combines different features of state, action, and travel context and captures the dynamic properties of micro route choice, achieving competitive interpretability of micro travel decision-making [69].…”
Section: Models With Information Factors Consideredmentioning
Urban day-to-day travel systems generally exist in various types of cities. Their modeling is difficult due to the uncertainty of individual travelers in micro travel decision-making. Moreover, with the advent of the information age, intelligent connected vehicles, smartphones, and other types of intelligent terminals have placed urban day-to-day travel systems in an information environment. In such an environment, the travel decision-making processes of travelers are significantly affected, making it even more difficult to give theoretical explanations for urban day-to-day travel systems. Considering that analyzing urban day-to-day travel patterns in an information environment is of great significance for governing the constantly developing and changing urban travel system and, thus, of great importance for the sustainable development of cities, this paper gives a systematic review of the theoretical research on urban day-to-day travel and its development in an information environment over the past few decades. More specifically, the basic explanation of an information environment for urban day-to-day travel is given first; subsequently, the theoretical development of micro decision-making related to individual day-to-day travelers in an information environment is discussed, and the theoretical development related to changes in urban macro traffic flow, which can be recognized as the aggregation effect formed by individual micro decision-making, is also discussed; in addition, the development of understanding different types of traffic information that travelers may obtain in an information environment is discussed; finally, some important open issues related to the deep impact of information environment on urban day-to-day travel systems that require further research are presented. These valuable research directions include using information methods to fit day-to-day travel patterns of cities and implementing macro and micro integrated modeling for urban day-to-day travel systems based on complex system dynamics and even quantum mechanics.
“…Li et al [34] proposed an DRL method based on an attention mechanism, which contains a vehicle selection decoder considering heterogeneous fleet constraints and a node selection decoder considering route construction. Nai et al [35] proposed a mixedstrategy gradient actor-critic model with a stochastic escape term and a filtering operation, using a model-driven approach to ensure the convergence speed of the whole model. Berat et al [36] proposed a synergistic combination of deep reinforcement learning and hierarchical game theory as a modelling framework for driver behaviour prediction in motorway driving scenarios.…”
To address urban traffic congestion, researchers have made various efforts to mitigate issues such as prolonged travel time, fuel wastage, and pollutant emissions. These efforts primarily involve microscopic route selection from the vehicle perspective, multi-vehicle route optimization based on traffic flow information and historical data, and coordinated route optimization that models vehicle interaction as a game behavior. However, existing route selection algorithms suffer from limitations such as a lack of heuristic, low dynamicity, lengthy learning cycles, and vulnerability to multi-vehicle route conflicts. To further alleviate traffic congestion, this paper presents a Period-Stage-Round Route Selection Model (PSRRSM), which utilizes a population game between vehicles at each intersection to solve the Nash equilibrium. Additionally, a Period Learning Algorithm for Route Selection (PLA-RS) is proposed, which is based on a multi-agent deep deterministic policy gradient. The algorithm allows the agents to learn from the population game and eventually transition into autonomous learning, adapting to different decision-making roles in different periods. The PSRRSM is experimentally validated using the traffic simulation platform SUMO (Simulation of Urban Mobility) in both artificial and real road networks. The experimental results demonstrate that PSRRSM outperforms several comparative algorithms in terms of network throughput and average travel cost. This is achieved through the coordination of multi vehicle route optimization, facilitated by inter-vehicle population games and communication among road agents during training, enabling the vehicle strategies to reach a Nash equilibrium.
“…Data has shown that China's urbanization process has been continuously accelerating, at the end of the year 2021, the urbanization rate of China's resident population has reached up to 64.72% [1]. In the expanding scale of large and medium-sized cities, limited urban transportation resources and increasing transportation demand have formed a significant supply-demand contradiction [2]. It is very important to achieve effective governance of urban transportation and solve congestion problems as much as possible, and such effective governance relies on a deep understanding of the rules of urban transportation travel.…”
The study of road traffic flow theory utilizes physics and applied mathematics to analyze relevant parameters and their relationships quanlitatively and quantitatively, in order to explore their dynamic changes. The fluid dynamics model used for traffic flow analysis is highly favored by scholars due to its solid mathematical foundation and good simulation results. However, existing models have two main shortcomings: firstly, existing research is mostly limited to non-viscoelastic fluid equation or incompressible non-Newtonian fluid equation, making it difficult to accurately describe the viscosity state and micro cluster properties of the actual traffic flow; secondly, the existing non-Newtonian fluid partial differential equations (PDEs) rely heavily on the finite element method (FEM) for solving, requiring higher computational cost, larger storage space, and more constraint conditions. Thus, in this paper, a traffic flow equation based on compressible non-Newtonian fluid has been constructed, and it has been solved by using physical-informed rational neural network (PIRNN) and noise heavy-ball acceleration gradient descent (NHAGD) to ensure learning and training speed and accuracy. Numerical results indicate that the proposed method can truly reflect the gradual change process in the viscosity of traffic flow, and has better solving performance than traditional FEM and physical-informed neural network (PINN) with activation functions; under the same conditions, the prediction error of the proposed method is also smaller than that of traditional traffic flow models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.