Figure 1 - uploaded by Quan Yuan
Content may be subject to copyright.
Source publication
Purpose-The rapid development of Intelligent and Connected Vehicles (ICVs) has boomed a new round of global technological and industrial revolution in recent decades. The Technology Roadmap of Intelligent and Connected Vehicles (2020) comprehensively analyzes the technical architecture, research status and future trends of ICVs. The methodology tha...
Contexts in source publication
Context 1
... rows" refers to the vehicle technologies, the information interaction technologies and basic support technologies involved in ICVs. "Two columns" refers to the on-board platforms and infrastructure supporting the development of ICVs, as shown in Figure 1. ...
Context 2
... most substantial contribution of the roadmap is the section on the ICV technologies. In the roadmap, the ICV technology development is firstly planned in three main areas: vehicular technology, information interaction and basic support technology, as shown in Figure 1. Then, the technology roadmap of 16 technical sub-areas is explained in detail. ...
Citations
... The development of vehicle-to-everything (V2X) communication technologies has greatly enhanced the accessibility of trajectory data (Peng et al., 2021;Xu et al., 2022). This valuable data source provides a continuous and reliable means to obtain real-time traffic state information, which can be used for platoon control (D. ...
Trajectory data from connected vehicles (CVs) provide a continuous and reliable means of obtaining information that can be leveraged to optimize traffic signals. This paper proposes a real‐time traffic signal control method using CV trajectory data as the sole input. The primary goal of the proposed signal control method is to prevent queue spillover, which may significantly decrease the traffic efficiency on urban networks and induce high delays to the travelers. The proposed method formulates the signal control problem via a linear quadratic optimization model, considering the constraints related to the duration and variability of green lights in practical traffic signal control systems. Compared to conventional max‐pressure‐based methods, the optimization model offers enhanced efficiency in handling these constraints, making it highly suitable for real‐life implementation. The proposed method has undergone testing in both simulated environments and real‐world applications. In the simulation experiments, the proposed method has been demonstrated to effectively reduce spillover risks and outperform a conventional max‐pressure‐based approach even when the CV penetration rate is as low as 5%. In the real‐world experiment, the proposed method had been tested in a traffic network around the Beijing Capital International Airport for several months. The severity of spillovers, which was represented by two performance indicators, had been significantly reduced after implementing the proposed method.
... [26] GRL in different fields 2022 Typical GRL-based algorithms and applications in several fields were generally summarized. [29] GRL in different fields 2022 Basic knowledge and general technology roadmap of CAVs were mainly summarized. ...
... The GRL-based methods for transportation systems were summarized; however, there was no discussion on decision-making for CAVs using GRL-based methods in this article. In [29], the fundamental knowledge and general technology roadmap from several aspects (environmental perception, decision-making, collaboration, etc.) of CAVs was mainly reviewed. However, the summary of decision-making algorithms was insufficient. ...
The proper functioning of connected and autonomous vehicles (CAVs) is crucial for the safety and efficiency of future intelligent transport systems. Meanwhile, transitioning to fully autonomous driving requires a long period of mixed autonomy traffic, including both CAVs and human-driven vehicles. Thus, collaborative decision-making technology for CAVs is essential to generate appropriate driving behaviors to enhance the safety and efficiency of mixed autonomy traffic. In recent years, deep reinforcement learning (DRL) methods have become an efficient way in solving decision-making problems. However, with the development of computing technology, graph reinforcement learning (GRL) methods have gradually demonstrated the large potential to further improve the decision-making performance of CAVs, especially in the area of accurately representing the mutual effects of vehicles and modeling dynamic traffic environments. To facilitate the development of GRL-based methods for autonomous driving, this paper proposes a review of GRL-based methods for the decision-making technologies of CAVs. Firstly, a generic GRL framework is proposed in the beginning to gain an overall understanding of the decision-making technology. Then, the GRL-based decision-making technologies are reviewed from the perspective of the construction methods of mixed autonomy traffic, methods for graph representation of the driving environment, and related works about graph neural networks (GNN) and DRL in the field of decision-making for autonomous driving. Moreover, validation methods are summarized to provide an efficient way to verify the performance of decision-making methods. Finally, challenges and future research directions of GRL-based decision-making methods are summarized.
... 4) Policy support. Countries worldwide have launched technology roadmaps, such as China's TRICV project, the USA's CARMA project, Germany's Ko-HAF project, and the EU's 5GCAR project, to promote CAV marketization[60]. ...
Oversaturation has become a serious issue for urban intersections worldwide due to the rapid increase in population and traffic demands. The emergence of connected and automated vehicle (CAV) technologies demonstrates the potential to improve oversaturated arterial traffic. Integrating vehicular control and intersection controller optimization into a single process based on CAV technologies can optimize the performance of mixed traffic flow scenarios with various levels of CAV market penetration. This paper proposes an efficient reservation-based cooperative ecodriving model (RCEM) for an isolated intersection under partial and complete CAV market penetration, which can simultaneously optimize the CAV trajectories and intersection controller. CAVs are utilized to precluster manual vehicles into a platoon to improve vehicle passage efficiency. Then, a heuristic-based algorithm is developed to effectively obtain an optimal solution. The proposed RCEM scheme is compared with fixed signal control and actuated signal control in a Simulation of Urban MObility (SUMO)-based platform. Experimental results prove that the RCEM scheme outperforms the fixed signal control and actuated signal control in terms of stop delay, fuel consumption, and emissions under the condition of low levels of CAV penetration. Sensitivity analysis indicates that the system performance further improves as the CAV penetration rate increases, and the stop delay is almost eliminated when the CAV market penetration reaches 100%. Furthermore, the vehicle delay fluctuation under left-turning rates ranging from 5%-75% is 4.4 sec, which is far better than the vehicle delay fluctuation of the fixed signal control (176 sec) and actuated control (65.6 sec).
... Potential applications span a variety of fields, such as intelligent transportation, smart cities, and autonomous driving. [42][43][44][45][46][47] As our research progresses, we are optimistic about the broader applicability of this model in tackling complex sequence prediction problems across diverse disciplines. This study serves as a stepping stone towards harnessing the power of language models in practical real-world scenarios, and we look forward to the remarkable advancements that lie ahead. ...
Language models have contributed to breakthroughs in interdisciplinary research, such as protein design and molecular dynamics understanding. In this study, we reveal that beyond language, representations of other entities, such as human behaviors, that are mappable to learnable sequences can be learned by language models. One compelling example is the real-world delivery route optimization problem. We here propose a novel approach based on the language model, to optimize delivery routes based on drivers’ historical experiences. While a broad range of optimization-based approaches has been designed to optimize delivery routes, they do not capture the implicit knowledge of complex delivery operating environments. The model we propose integrates this knowledge in the route optimization process by learning from driving behaviors in experienced drivers. A real-world delivery route that preserves the drivers’ implicit behavioral patterns is first analogized to a sentence in natural language. Through unsupervised learning, we then learn the vector representations of words and infer the drivers’ delivery chains based on the tailored chain reaction-based algorithm. We also provide insights into the fusion of language models and operations research methods. In our approach, language models are applied to learn drivers’ delivery behaviors and infer new deliveries at the delivery zone level, while the classic traveling salesman problem (TSP) model is embedded into the hybrid framework for intra-zone optimization. Numerical experiments performed on real-world data from Amazon’s delivery service demonstrate that the proposed approach outperforms pure optimization, supporting the effectiveness, efficiency, and extensibility of our model. As a versatile approach, the proposed framework can easily be extended to various disciplines where the data follow certain grammar rules. We anticipate that our work will serve as a stepping stone toward the understanding and application of language models in tackling interdisciplinary research problems.
Roadside sensing units' (RSUs) perception capability may be substantially impaired by occlusion issue even they work cooperatively. However, the joint influence of static and dynamic occlusions in real-life situations remains inadequately considered in optimizing RSUs' placement. This study proposes a virtual-real-fusion simulation (VRFS) framework that combines traffic simulation and point clouds of real-world road environment to optimize RSUs' deployment. Point clouds and triangular meshes are used to model static and dynamic obstacles, respectively. A structure-retained spherical projection method is developed to efficiently emulate RSUs' data collection. Based on the developed VRFS, the probabilistic occupancy maps (POM) are created to represent traffic scenarios. The POM-based cross entropy (CE) is proposed as the surrogate metric for evaluating the detection performance of cooperative RSUs. The Bayesian optimizer is applied to optimize the RSUs' placement parameters (decision variables) by minimizing CE. Test results show that it is viable to use the POM-based CE as a proxy for evaluating cooperative RSUs' sensing performance. Considering the occlusion effect adds to the efficacy of POM-based CE as a surrogate metric. Compared with traffic volume, the adverse effect of the proportion of large vehicles on RSUs' detection performance is more significant. There are no significant patterns regarding how the optimized RSU positions vary with traffic parameters. The comparisons with existing methods further verify the importance of considering both static and dynamic occlusions in optimizing RSUs' placement. Besides, the proposed method can yield better optimization results more efficiently than existing approaches.
Talent is crucial for accelerating the growth of China's intelligent connected vehicle (ICV) industry. To gain insights into talent flow within the industry, we propose the Technology-Profession Method to construct a large-scale dataset based on granted patents from China National Intellectual Property Administration and resumes from Zhaopin, an online recruitment platform. By utilizing this method, we accurately identify 175,798 talents and collect 239,479 pieces of talent flow data. Additionally, we introduce the Stage-Level Framework to comprehensively map the talent flow. This framework encompasses multiple directed networks spanning two stages of talent careers and three levels ranging from micro to macro. Furthermore, we employ the Global Moran's I and the Local Indicators of Spatial Association to examine the spatial autocorrelation of talent flow. The results reveal significant variations in talent flow across different subindustries, stages and levels within China's ICV industry. Notably, there is a pronounced spatial autocorrelation of talent flow between companies, particularly in South China. Factors such as spatial distance, economic development, and industrial agglomeration influence the patterns of talent flow. These findings offer valuable insights for policy makers, providing guidance on how to effectively manage and intervene in talent flow within the ICV industry.
With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem. Current autonomous driving datasets can broadly be categorized into two generations.
The first-generation autonomous driving dataset are characterized by relatively simpler sensor modalities, smaller dataset scales, and and are limited to perception-level tasks. KITTI, introduced in 2012, serves as a prominent representative of this initial wave. In contrast, the second-generation datasets exhibit heightened complexity in sensor modalities, greater dataset scale and diversity, and an expansion of tasks from perception to encompass prediction and control. Leading examples of the second generation include nuScenes and Waymo, introduced around 2019. This comprehensive review, conducted in collaboration with esteemed colleagues from both academia and industry, systematically assesses over seventy open-source autonomous driving datasets from domestic and international sources. It offers insights into various aspects, such as the principles underlying the creation of high-quality datasets, the pivotal role of data within algorithmic closed-loop systems, and the utilization of generative foundation models to facilitate scalable data generation. Furthermore, this review undertakes an exhaustive analysis and discourse regarding the characteristics and data scales that future third-generation autonomous driving datasets should possess. It also delves into the scientific and technical challenges that warrant resolution. The synthesis and perspectives presented in this article provide valuable guidance for the development of a novel generation of autonomous driving datasets and ecosystems. These endeavors are pivotal in advancing autonomous innovation and fostering technological enhancement in critical domains.
Potential field theory, as a theory that can also be applied to vehicle control, is an emerging risk quantification approach to accommodate the connected and self-driving vehicle environment. Vehicles have different risk impact effects on other road participants in each direction under the influence of road rules. This variability exhibited by vehicles in each direction is not considered in the previous potential field model. Therefore, this paper proposed a potential field model that takes the anisotropy of vehicle impact into account: (1) introducing equivalent distances to separate the potential field area in the different directions before and after the vehicle; (2) introducing co-virtual forces to characterize the effect of the side-by-side travel phenomenon on vehicle car-following travel; (3) introducing target forces and lane resistance, which regress the control of desired speed to control the acceptable risk of drivers. The Next Generation Simulation (NGSIM) dataset is used in this study to create the model's initial parameter values based on the artificial swarm algorithm. The simulation findings indicate that when the vehicle is given the capacity to perceive the surrounding traffic environment, the suggested the anisotropic safety potential field model (ASPFM) performs better in terms of driving safety.
Lane-changing behaviour is one of the most important and basic driving behaviours. Intelligent and connected vehicles must face lane-changing scenarios to achieve autonomous driving. To improve the rationality of lane-changing trajectory planning for intelligent vehicles, by analysing numerous real vehicle lane-changing trajectories in the German HighD natural driving dataset, a dimensionless lateral quantification balance index is proposed to realise a comprehensive and objective evaluation of the degree of human-likeness of lane change trajectory planning. Focused on the lateral kinematic characteristics of lane changing, a lane-changing trajectory extraction method based on the peak-to-peak value of lateral acceleration is proposed. Lateral displacement, lateral velocity, lateral acceleration and lane-changing duration are extracted from natural driving data, and the correlations between the parameters are revealed to deduce the lateral quantification balance index. With several common parametric lane-changing trajectory models of intelligent vehicles, such as sine, quintic polynomial, Gaussian and hyperbolic tangent and fifth-order Bessel models, as examples, the index values of each lane-changing trajectory model are calculated and obtained. Results show that the proposed index can balance the different requirements in lane-changing efficiency and comfort of the trajectory parameters during the lane-changing process, thus achieving a comprehensive quantitative evaluation of lateral stability, efficiency and comfort. This research establishes an intuitive and concise objective function for human-like trajectory planning and provides a basis for trajectory tracking control and real-time dynamic correction of intelligent vehicles.
