Ensuring the reliability of autonomous driving perception systems requires extensive environment-based testing, yet real-world execution is often impractical. Synthetic datasets have therefore emerged as a promising alternative, offering advantages such as cost-effectiveness, bias free labeling, and controllable scenarios. However, the domain gap between synthetic and real-world datasets remains a major obstacle to model generalization. To address this challenge from a data-centric perspective, this paper introduces a profile extraction and discovery framework for characterizing the style profiles underlying both synthetic and real image datasets. We propose Style Embedding Distribution Discrepancy (SEDD) as a novel evaluation metric. Our framework combines Gram matrix-based style extraction with metric learning optimized for intra-class compactness and inter-class separation to extract style embeddings. Furthermore, we establish a benchmark using publicly available datasets. Experiments are conducted on a variety of datasets and sim-to-real methods, and the results show that our method is capable of quantifying the synthetic-to-real gap. This work provides a standardized profiling-based quality control paradigm that enables systematic diagnosis and targeted enhancement of synthetic datasets, advancing future development of data-driven autonomous driving systems.

Neural rendering with Gaussian splatting has advanced novel view synthesis, and most methods reconstruct surfaces via post-hoc mesh extraction. However, existing methods suffer from two limitations: (i) inaccurate geometry in texture-less indoor regions, and (ii) the decoupling of mesh extraction from optimization, thereby missing the opportunity to leverage mesh geometry to guide splat optimization.In this paper, we present OMeGa, an end-to-end framework that jointly optimizes an explicit triangle mesh and 2D Gaussian splats via a flexible binding strategy, where spatial attributes of Gaussian Splats are expressed in the mesh frame and texture attributes are retained on splats. To further improve reconstruction accuracy, we integrate mesh constraints and monocular normal supervision into the optimization, thereby regularizing geometry learning. In addition, we propose a heuristic, iterative mesh-refinement strategy that splits high-error faces and prunes unreliable ones to further improve the detail and accuracy of the reconstructed mesh. OMeGa achieves state-of-the-art performance on challenging indoor reconstruction benchmarks, reducing Chamfer-L1by 47.3% over the 2DGS baseline while maintaining competitive novel-view rendering quality. The experimental results demonstrate that OMeGa effectively addresses prior limitations in indoor texture-less reconstruction.

In contemporary society, autonomous driving systems face enormous challenges in various aspects, including the environment, traffic participants, and communication. The primary task of achieving vehicle autonomy is to ensure that Connected and Automated Vehicles (CAVs) can cooperate safely and efficiently with Human-Driven Vehicles (HDVs). Previous research mainly focused on strategies for purely CAV scenarios or treated HDVs as random factors in traffic, with relatively few studies considering the synchronous inducement and control of both types of vehicle within a unified framework. This research focuses on mixed traffic flow that includes both HDVs and CAVs, specifically addressing the merging problem at highway on-ramp entrances. We propose an inducement control method and a planning framework that target both types of vehicles simultaneously. For upstream HDVs, speed inducement is implemented based on time series predictions, along with behavior modeling that includes both internal and external uncertainties using a Gaussian mixture model. For ramp vehicles, merging decisions are made while considering the uncertainties of the upstream vehicles. Furthermore, based on the speed inducement strategy and the decision module, a cooperative uncertainty-aware planning model is constructed to achieve motion planning. The research demonstrates that the proposed speed inducement strategy can improve traffic safety and driver experience, and the cooperative control framework designed for both types of vehicles exhibits real-time functionality and performs excellently in terms of computation speed and planning success rates.

Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space created by unexpected faults. Second, transitions recorded before and after faults in the replay buffer affect training unevenly, leading to a sample imbalance problem. To overcome these challenges, this paper enhances the fault tolerance of MARL by combining optimized model architecture with a tailored training data sampling strategy. Specifically, an attention mechanism is incorporated into the actor and critic networks to effectively and automatically detect fault information and dynamically regulate the attention given to faulty agents. Additionally, a prioritization mechanism is introduced to selectively sample transitions critical to current training needs. To further support research in this area, we design and open-source a highly decoupled code platform for fault-tolerant MARL, aimed at improving the efficiency of studying related problems. Experimental results demonstrate the effectiveness of our method in handling various types of faults, faults occurring in any agent, and faults arising at random times. Note to Practitioners—Multi-agent systems based on MARL outperform those using traditional control methods in terms of performance but remain highly vulnerable to unexpected faults. To improve fault tolerance in such systems, we introduce an attention mechanism that enables the neural network to dynamically adjust its focus on fault-related information. Additionally, a prioritization sampling strategy is employed to select critical samples from collected experiences that are most relevant to current training needs. Experimental results across various fault types demonstrate significant improvements in fault tolerance, validating the robustness of our approach. These findings suggest that the proposed method has the potential to be applied to real-world scenarios, such as multi-robot systems and autonomous vehicle fleets.

Driving risk field (DRF) emerges as an effective way to assess the driving safety of connected and automated vehicles (CAVs). Most existing DRF models are established from the so-called birds-eye-view (BEV), which limits their accuracy for distributed vehicle-level tasks such as trajectory planning since the interactions between ego vehicle (EV) and its surrounding traffic environment have not been fully considered. To fill this research gap, we establish a novel DRF model from ego-vehicle-view (EVV) and apply it in trajectory planning in this paper. Firstly, the collision boundary between EV and its surrounding obstacles is defined by introducing the elliptical model to fully consider the geometry characteristics of vehicles. Secondly, the relative motion influence coefficient is designed to accurately characterize the relative motion between EV and obstacles, instead of using only basic driving state information such as location and velocity. On this basis, the unified DRF is established from EVV for driving safety assessment, which contains vehicle risk field (VRF) and lane marking risk field (LMRF). Based on the established DRF model, we then design a rolling trajectory planning method (RTPM) with a rolling horizon strategy, which not only ensures a long prediction horizon but also effectively reduces the computational complexity. Multiple simulation results under different traffic scenarios jointly verify the accuracy and applicability of the proposed RTPM and DRF model established from this new perspective.

Cooperative driving is emerging as an effective way to improve traffic efficiency and safety, and has attracted considerable research attention. However, a major drawback of most existing studies is that they rely on ideal communication conditions and overlook the critical issue of communication failures in vehicles. These failures have the potential to disrupt traffic efficiency and introduce serious safety risks. In this paper, we propose a fault-tolerant cooperative driving strategy that systematically addresses the challenges posed by communication failures within a global planning and local gaming framework. In the global planning stage, the centralized controller coordinates the passing order of all vehicles to optimize traffic efficiency. In the local gaming stage, the faulty vehicle engages in a two-player cooperative game to decide the order with potentially conflicting vehicles. Simulation results show that our strategy enhances the fault tolerance of the system, ensuring driving safety while mitigating the impact of faults on traffic efficiency. This work provides insights for building a more robust and safe cooperative driving system under real-world communication challenges.

Sampling, generation, and evaluation of scenarios are essential steps for intelligent testing of autonomous vehicles. Since uncertainty in driving behavior always leads to different occurrence frequencies of scenarios, we have to sample these scenarios in naturalistic datasets. Furthermore, a specified scenario needs to be further enriched and the driving behavior within it needs to be fully described to carry out generation in simulation systems. However, existing approaches generate scenarios randomly and uncontrollably, which makes them unable to precisely generate the specified scenarios. The driving behavior they describe is also memoryless and inflexible. To address the two issues, we propose a task-driven controllable scenario generation framework that can generate scenarios with the consideration of the driving behavior of Surrounding Vehicles (SVs) in a controllable manner. We first manually assign the driving behavior based on different testing tasks for all the considered vehicles. Then we expand the driving behavior temporally as the continuation and transition of several motion activities and generate the corresponding vehicle trajectories spatially. We adopt And-Or Graph (AOG) to model the transition between these motion activities. In contrast to the common memoryless Markov process, our framework generates driving behavior with continuity and driving memory. Finally, we evaluate our framework by generating lane-changing scenarios.

Connected and automated vehicles (CAVs) are expected to play a vital role in the emerging intelligent transportation system. In recent years, researchers have proposed various cooperative driving methods for CAVs, and there is an urgent need for a generic and unified traffic simulator to simulate and evaluate these methods. However, traditional traffic simulators have two critical deficiencies for CAV simulation needs: 1) the planning and dynamical modeling of vehicles in traditional simulators are based on a feedback mode, which is incompatible with the feed-forward decision and planning that CAVs commonly adopt; 2) the traditional simulators cannot provide typical traffic scenarios and corresponding standardized algorithms for multi-CAV cooperative driving. In this paper, we introduce CAVSim, a novel microscopic traffic simulator for CAVs, to address these deficiencies. CAVSim is developed modularly according to the emerging technology of the CAV environment, emphasizes feed-forward decision and planning for CAVs, and highlights the cooperative decision and planning components in the CAV environment. CAVSim incorporates rich and typical traffic scenarios and provides standardized cooperative driving algorithms and comparable performance metrics for multi-CAV cooperative driving. With CAVSim, researchers can conveniently deploy decision, planning, and control methods for CAVs at different levels, evaluate their performance, compare them with the standardized algorithms incorporated in CAVSim, and even further explore their impact on traffic flow. As a unified platform for CAVs, CAVSim can facilitate the studies on CAVs and promote the advancement of methods and techniques for CAVs.

Road shoulders and slopes often appear in unstructured environments. They make 2.5D vehicle trajectory planning commonly seen in our daily life, which lies on a 2D manifold embedded in a 3D space. The height difference of these terrains brings spatially dependent constraints on vehicle maneuvers, such as the limit on vehicle steering for vehicle tire protection when a vehicle approaches a road shoulder edge. These constraints have an “if-else” structure since they are activated only when the vehicle passes through the local area with a height difference, making the restriction on variables coupled with the judgment of variables. This makes the application of state-of-art optimization-based planners challenging. To solve this problem, we devise an approximation formulation for these constraints in the trajectory planning optimization problem, whose solution depends on a proper initial guess for the optimizer. We propose a two-stage trajectory planning framework, where the first stage improves the hybrid A* algorithm by adding spatially dependent constraints into node expansion to provide the initial guess. Then, the optimization problem with the formulated spatially dependent constraints is solved for further trajectory smoothness and quality. Finally, the simulation results validate the fast and high-quality planning performance of our proposed framework.

Recovering the three-dimensional structure information from a monocular camera is significant for automated driving, robot navigation, and traffic safety assessment. Recent work has solved various tight issues on self-supervised monocular depth estimation of leveraging on-board videos, such as occlusion/disocclusion, dynamic objects, and scale inconsistent. Nevertheless, rare work focuses on the model’s prediction confidence and underlying relations between depths, while they are essential for a decision-making system and performance improvement, respectively. This paper proposes a novel scheme, that of correlation-aware structure, to dig into the relations between depths, converting the independent depths into a graph-like connected depth map. Subsequently, a Gaussian estimator is devised to predict the depth map and uncertainty map concurrently. The uncertainty map can show us problematic regions where it is difficult to predict, from which we further develop uncertainty-based strategies to improve the performance. Specifically, we propose a simple image preprocessing method to overcome the gradient locality issue caused by low-texture, especially in smooth roads and shadows. Also, to avoid the influence of high-uncertainty regions, we propose a solidity-aware mask to recognize the reliable pixels for training in the image. The experiments on the KITTI dataset show that our method results in a competitive performance in both depth and ego-motion estimation tasks compared with the state-of-the-art methods. Besides, additional experiments on the Make3D and Cityscapes datasets demonstrate our method’s strong generalization capability and practicality.

Scene perception is essential for driving decision-making and traffic safety. However, fog, as a kind of common weather, frequently appears in the real world, especially in mountain areas, making it difficult to accurately observe the surrounding environments. Therefore, precisely estimating the visibility under foggy weather can significantly benefit traffic management and safety. To address this, most current methods use professional instruments outfitted at fixed locations on the roads to perform the visibility measurement; these methods are expensive and less flexible. In this paper, we propose an innovative end-to-end convolutional neural network framework to estimate the visibility leveraging Koschmieder’s law and the image data. The proposed method estimates the visibility by integrating the physical model into the proposed framework, instead of directly predicting the visibility value via the convolutional neural network. Moreover, we estimate the visibility as a pixel-wise visibility map against those of previous visibility measurement methods which solely predict a single value for the entire image. Thus, the estimated result of our method is more informative, particularly in uneven fog scenarios, which can benefit to developing a more precise early warning system for foggy weather, thereby better protecting the intelligent transportation infrastructure systems and promoting their development. To validate the proposed framework, a virtual dataset, FACI, containing 3,000 foggy images in different concentrations, is collected using the AirSim platform, which is available athttps://github.com/coutyou/FoggyAirsimCityImages. Detailed experiments show that the proposed method achieves performance competitive to those of state-of-the-art methods.

In consideration of the convenience of drivers' operations, a velocity guide driving model for collision avoidance in non-signalized intersection is proposed. Based on reduplicate game theory, a profit function consists of safety, rapidity, controlling indicators is redefined. Pareto optimality is adopted to obtain the strategies which maximize the profit for the whole game. Simulation results show that the model is effective and gives a more comfortable vehicle-cross process.

As one of the most promising communication technologies in vehicular networks, LTE V2X related technical specifications are released in Release 14 by 3GPP in 2017. In the newest specifications, the LTE V2X can work with or without eNBs, namely LTE-V-Cell and LTE-V-Direct. In this study, we focus on the media access process of LTE-V-Direct. First, we proposed a model to describe the MAC process of LTE-V-Direct, and based on that model, we derived the Frame Information Loss Rate and Inter-Reception Gap of LTE-V-Direct. Then, we designed a simulation to verify the model. By comparing the simulation result and numerical result of the model, the correctness and precision of the model is verified.

V2V (Vehicle to Vehicle) is recently seen as a very promising technology to avoid accidents and to relieve traffic congestion in transportation. DSRC (Dedicated Short Range Communication) is the most polular communication technology that could be used in V2V system. To figure out what extent DSRC could support typical V2V applications, this paper proposed a performance evaluation method. Firstly, we use cellular automata model to generate the spatial distribution of the vehicles. Then we simulated the procedure of V2V message propagation both as physical and MAC layer of DSRC. Compared with most of the analysis model, hidden terminal issue was taken into consideration as well. Based on the vehicles distribution and the message propagation procedure, we conducted an application-oriented performance evaluation of DSRC based on a typical application, namely FCW (Forward Collision Warning). Simulation results show that communication performance could not meet the need of safety related application under some circumstances, promotions should be fulfilled to guarantee the reliability of V2V applications.

Risky driving is a major cause of traffic accidents. In this paper, we propose a new method that recognizes risky driving behaviors purely based on vehicle speed time series. This method first retrieves the important distribution pattern of the sampled positive speed-change (value and duration) tuples for individual drivers within different speed ranges. Then, it identifies the risky drivers based on different patterns of drivers. Tests show the effectiveness of the proposed method. Since speed measurement is available on most of the newly build vehicles, this method can be easily implemented and used. The conclusion is useful to many traffic applications, e.g., driver training and insurance pricing.

During the last 60 years, incessant efforts have been made to improve the efficiency of traffic control systems to meet ever-increasing traffic demands. Some recent works attempt to enhance traffic efficiency via vehicle-to-vehicle communications. In this paper, we aim to give a survey of some research frontiers in this trend, identifying early-stage key technologies and discussing potential benefits that will be gained. Our survey focuses on the control side and aims to highlight that the design philosophy for traffic control systems is undergoing a transition from feedback character to feedforward character. Moreover, we discuss some contrasting preferences in the design of traffic control systems and their relations to vehicular communications. The first pair of contrasting preferences are model-based predictive control versus simulation-based predictive control. The second pair are global planning-based control versus local self-organization-based control. The third pair are control using rich information that may be highly redundant versus control using concise information that is necessary. Both the potentials and drawbacks of these control strategies are explained. We hope these comparisons can shed some interesting light on future traffic control studies.

This paper focuses on the influence on traffic flow characteristics of distance between on-ramp and off-ramp in expressway. In this research, those characteristics include traffic flow rate, average speed and average density. Based on VISSEVI, we calibrated key parameters and a calibrating procedure is proposed. Then we simulated scenarios with different distances from 100m to 1000m. Analyses of the distance's influence on traffic flow characteristics are studied using simulation results. A step further, 3 modes are classified out of different distances and 2 thresholds are proposed. The two thresholds are within 100-200m and 500-600m and if distance varies through these, traffic flow characteristics will change significantly. Finally, as for verification, we compared 3 scenarios of simulation with reality. In the future, different control strategies may be applied due to different conditions.

With the dramatic development of image processing technology, a growing number of traffic flow detection and analyses have been conducted by using video data. Time to collision (TTC) and postencroachment time (PET) are two major parameters used to indicate the severity of a potential collision and to capture an imminent vehicular accident. However, microlevel pedestrian-involved collisions are less studied because they are hard to observe or record. This paper tries to extract the traffic object locations from video data, to define the time difference to collision (TDTC) parameter as a variation from TTC and PET to fit the pedestrian-involved potential collisions/conflicts, analyze the interaction behavior between pedestrian and vehicles, and validate the TDTC parameter in indicating pedestrian safety performance by using 100 groups of interaction data. The results show that the interaction cases with larger TDTC values are safer, whereas the cases with continuously closer to zero TDTC values are more dangerous. About 80% of the cases classified by the TDTC parameter have the same result with the independent observation; if TDTC is combined with vehicle speed, the classification result can be improved. More mixed traffic scenes will be conducted based on this research in the future.

This paper studies cooperative signal strategies for Beijing expressway ramping control. Particularly, the distance between on-ramp and off-ramp ranges from 100m to 1000m. Four signal control strategies are proposed and tested under 3 kinds of traffic flow states and 38 kinds of road network structures in VISSIM. Results indicate that the cooperative signal control is an effective way to enhance road capacity and alleviate congestions in urban expressway. Moreover, the control efficiencies in different traffic scenarios are discussed, too.

This paper studies the following driving scenario that is common in China and many Asian developing countries: a bus has to temporarily occupy the bicycle lane in order to stop and pick up passengers, where the mixed traffic flow is composed of motorized vehicles and bicycles. A special cellular automation model is proposed to examine the governing factors that influence the delay of a bus near a bus stop. Vehicle inflow rate, bicycle inflow rate and bus inflow rate are specially addressed. Finally, some useful suggestions are presented.

It is important to calibrate the position and attitude precision for space manipulator in laboratory environment. The construction goal of the calibration system for a space manipulator is to simulate the microgravity environment in space, to counterbalance the impact of gravity on manipulator and to realize the test of 3D position precision, attitude and trajectory precision in the terrestrial environment. This paper introduces a novel calibration system. Based on the definitions of five kinds of reference frames, this paper illustrates the relationships among the reference frames and the coordinate transformation method between the relevant reference frames. Furthermore, the paper defines four calibration items. Finally, a calibration case study is presented in detail, which verifies the availability of mechanical interface, air-bearing test-bed and air-bearing feet