Application Research of an Intelligent Detection Algorithm for Vehicle Trajectory Route Deviation

In the vehicle trajectory application system, it is often necessary to detect whether the vehicle deviates from the specified route. Trajectory planning in the traditional route deviation detection is defined by the driver through the mobile phone navigation software, which plays a more auxiliary driving role. This paper presents a method of vehicle trajectory deviation detection. Firstly, the manager customizes the trajectory planning and then uses big data technologies to match the deviation between the trajectory planning and the vehicle trajectory. Finally, it achieves the supervisory function of the manager on the vehicle track route in real-time. The results show that this method could detect the vehicle trajectory deviation quickly and accurately, and has practical application value.

A Probabilistic Architecture of Long-Term Vehicle Trajectory Prediction for Autonomous Driving

In mixed and dynamic traffic environments,accurate long-term trajectory forecasting of surrounding vehicles is one of the indispensable preconditions for autonomous vehicles to accomplish reasonable behavioral decisions and guarantee driving safety.In this paper,we propose an integrated probabilistic architecture for long-term vehicle trajectory prediction,which consists of a driving inference model(DIM)and a trajectory prediction model(TPM).The DIM is designed and employed to accurately infer the potential driving intention based on a dynamic Bayesian network.The proposed DIM incorporates the basic traffic rules and multivariate vehicle motion information.To further improve the prediction accuracy and realize uncertainty estimation,we develop a Gaussian process-based TPM,considering both the short-term prediction results of the vehicle model and the driving motion characteristics.Afterward,the effectiveness of our novel approach is demonstrated by conducting experiments on a public naturalistic driving dataset under lane-changing scenarios.The superior performance on the task of long-term trajectory prediction is presented and verified by comparing with other advanced methods.

A privacy-preserving vehicle trajectory clustering framework

As one of the essential tools for spatio‒temporal traffic data mining,vehicle trajectory clustering is widely used to mine the behavior patterns of vehicles.However,uploading original vehicle trajectory data to the server and clustering carry the risk of privacy leakage.Therefore,one of the current challenges is determining how to perform vehicle trajectory clustering while protecting user privacy.We propose a privacy-preserving vehicle trajectory clustering framework and construct a vehicle trajectory clustering model(IKV)based on the variational autoencoder(VAE)and an improved K-means algorithm.In the framework,the client calculates the hidden variables of the vehicle trajectory and uploads the variables to the server;the server uses the hidden variables for clustering analysis and delivers the analysis results to the client.The IKV’workflow is as follows:first,we train the VAE with historical vehicle trajectory data(when VAE’s decoder can approximate the original data,the encoder is deployed to the edge computing device);second,the edge device transmits the hidden variables to the server;finally,clustering is performed using improved K-means,which prevents the leakage of the vehicle trajectory.IKV is compared to numerous clustering methods on three datasets.In the nine performance comparison experiments,IKV achieves optimal or sub-optimal performance in six of the experiments.Furthermore,in the nine sensitivity analysis experiments,IKV not only demonstrates significant stability in seven experiments but also shows good robustness to hyperparameter variations.These results validate that the framework proposed in this paper is not only suitable for privacy-conscious production environments,such as carpooling tasks,but also adapts to clustering tasks of different magnitudes due to the low sensitivity to the number of cluster centers.

A hybrid data-driven and mechanism-based method for vehicle trajectory prediction

Ensuring the safe and efficient operation of self-driving vehicles relies heavily on accurately predicting their future trajectories.Existing approaches commonly employ an encoder-decoder neural network structure to enhance information extraction during the encoding phase.However,these methods often neglect the inclusion of road rule constraints during trajectory formulation in the decoding phase.This paper proposes a novel method that combines neural networks and rule-based constraints in the decoder stage to improve trajectory prediction accuracy while ensuring compliance with vehicle kinematics and road rules.The approach separates vehicle trajectories into lateral and longitudinal routes and utilizes conditional variational autoencoder(CVAE)to capture trajectory uncertainty.The evaluation results demonstrate a reduction of 32.4%and 27.6%in the average displacement error(ADE)for predicting the top five and top ten trajectories,respectively,compared to the baseline method.

Lane-Exchanging Driving Strategy for Autonomous Vehicle via Trajectory Prediction and Model Predictive Control

The cooperation between an autonomous vehicle and a nearby vehicle is critical to ensure driving safety in the laneexchanging scenario.The nearby vehicle trajectory needs to be predicted,from which the autonomous vehicle is controlled to prevent possible collisions.This paper proposes a lane-exchanging driving strategy for the autonomous vehicle to cooperate with the nearby vehicle by integrating vehicle trajectory prediction and motion control.A trajectory prediction method is developed to anticipate the nearby vehicle trajectory.The Gaussian mixture model(GMM),together with the vehicle kinematic model,are synthesized to predict the nearby vehicle trajectory.A potential-feldbased model predictive control(MPC)approach is utilized by the autonomous vehicle to conduct the lane-exchanging maneuver.The potential feld of the nearby vehicle is considered in the controller design for collision avoidance.On-road driving data verifcation shows that the nearby vehicle trajectory can be predicted by the proposed method.CarSim®simulations validate that the autonomous vehicle can perform the lane-exchanging maneuver and avoid the nearby vehicle using the proposed driving strategy.The autonomous vehicle can thus safely perform the laneexchanging maneuver and avoid the nearby vehicle.

Evaluation of Arterial Signal Coordination with Commercial Connected Vehicle Data: Empirical Traffic Flow Visualization and Performance Measurement

Emerging connected vehicle (CV) data sets have recently become commercially available, enabling analysts to develop a variety of powerful performance measures without deploying any field infrastructure. This paper presents several tools using CV data to evaluate traffic progression quality along a signalized corridor. These include both performance measures for high-level analysis as well as visualizations to examine details of the coordinated operation. With the use of CV data, it is possible to assess not only the movement of traffic on the corridor but also to consider its origin-destination (O-D) path through the corridor. Results for the real-world operation of an eight-intersection signalized arterial are presented. A series of high-level performance measures are used to evaluate overall performance by time of day, with differing results by metric. Next, the details of the operation are examined with the use of two visualization tools: a cyclic time-space diagram (TSD) and an empirical platoon progression diagram (PPD). Comparing flow visualizations developed with different included O-D paths reveals several features, such as the presence of secondary and tertiary platoons on certain sections that cannot be seen when only end-to-end journeys are included. In addition, speed heat maps are generated, providing both speed performance along the corridor and locations and the extent of the queue. The proposed visualization tools portray the corridor’s performance holistically instead of combining individual signal performance metrics. The techniques exhibited in this study are compelling for identifying locations where engineering solutions such as access management or timing plan change are required. The recent progress in infrastructure-free sensing technology has significantly increased the scope of CV data-based traffic management systems, enhancing the significance of this study. The study demonstrates the utility of CV trajectory data for obtaining high-level details of the corridor performance as well as drilling down into the minute specifics.

Six-DOF trajectory optimization for reusable launch vehicles via Gauss pseudospectral method

To be close to the practical flight process and increase the precision of optimal trajectory, a six-degree-offreedom（6-DOF） trajectory is optimized for the reusable launch vehicle（RLV） using the Gauss pseudospectral method（GPM）. Different from the traditional trajectory optimization problem which generally considers the RLV as a point mass, the coupling between translational dynamics and rotational dynamics is taken into account. An optimization problem is formulated to minimize a performance index subject to 6-DOF equations of motion, including translational and rotational dynamics. A two-step optimal strategy is then introduced to reduce the large calculations caused by multiple variables and convergence confinement in 6-DOF trajectory optimization. The simulation results demonstrate that the 6-DOF trajectory optimal strategy for RLV is feasible.

Estimation of Connected Vehicle Penetration on US Roads in Indiana, Ohio, and Pennsylvania

Connected vehicle data is an important assessment tool for agencies to evaluate the performance of freeways and arterials, provided there is sufficient penetration to provide statistically robust performance measures. A common concern by agencies interested in using crowd sourced probe data is the penetration rate across different types of roads, different hours of the day, and different regions. This paper describes and demonstrates a methodology that uses data from state highway performance monitoring systems in Indiana, Ohio and Pennsylvania. The study analyzes 54 locations over the 3 states for select Wednesdays and Saturdays in 2020 and 2021. Overall, across all locations and dates, the median penetration was approximately 4.5%. The median penetration for August 2020 for Indiana, Ohio, and Pennsylvania was 4.6%, 4.3%, and 4.0%, respectively. The median penetration for those same states in August 2020 on interstates and non-interstates was 3.9% and 4.6%, respectively. Additionally, the study conducted a longitudinal evaluation of Indiana penetration for selected months between January 2020 and June 2021. Indiana penetration increased modestly between December 2020 and June 2021, perhaps due to the post-COVID rebound of passenger vehicle traffic. This paper concludes by recommending that the techniques described in this paper be scaled to other states so that traffic engineers can make informed decisions on the use and limitations of connected vehicle data for various use cases.

Distribution of driving trajectory of passenger car in highway horizontal curves

In this paper the track behavior of passenger car was studied. The vehicle driving trajectory and driving direction were defined, and a classification of the type of vehicle trajectories along the curves was developed. The statistical parameters of vehicle trajectory samples in free flow and their frequency curves and cumulative frequency curves were achieved, K-S test and chi-square test were used to test normal distribution and gamma distribution for collected sample data, and the probabili- ty density functions were given. At last, dispersion degree between vehicle trajectory random varia- ble and the characteristic value of cumulative frequency curve in each key cross section in curves was analyzied. The proposed conclusion can provide theoretical support for the reasonable optimization of widen curve, design of alignment and the management of counter flow conflicts.

Trajectory-Based Data Forwarding Schemes for Vehicular Networks

This paper explains trajectory-based data forwarding schemes for multihop data delivery in vehicular networks where the trajectory is the GPS navigation path for driving in a road network. Nowadays, GPS-based navigation is popular with drivers either for efficient driv- ing in unfamiliar road networks or for a better route, even in familiar road networks with heavy traffic. In this paper, we describe how to take advantage of vehicle trajectories in order to design data-forwarding schemes for information exchange in vehicular networks. The design of data-forwarding schemes takes into account not only the macro-scoped mobility of vehicular traffic statistics in road net- works, but also the micro-scoped mobility of individual vehicle trajectories. This paper addresses the importance of vehicle trajectory in the design of multihop vehicle-to-infrastructure, infrastructure-to-vehicle, and vehicle-to-vehicle data forwarding schemes. First, we explain the modeling of packet delivery delay and vehicle travel delay in both a road segment and an end-to-end path in a road net- work. Second, we describe a state-of-the-art data forwarding scheme using vehicular traffic statistics for the estimation of the end-to- end delivery delay as a forwarding metric. Last, we describe two data forwarding schemes based on both vehicle trajectory and vehicu- lar traffic statistics in a privacy-preserving manner.

Integrated Performance Measures for Bus Rapid Transit System and Traffic Signal Systems Using Trajectory Data

Bus rapid transit (BRT) systems have been implemented in many cities over the past two decades. Widespread adoption of General Transit Feed Specification (GTFS), the deployment of high-fidelity bus GPS data tracking, and anonymized high-fidelity connected vehicle data from private vehicles have provided new opportunities for performance measures that can be used by both transit agencies and traffic signal system operators. This paper describes the use of trajectory-based data to develop performance measures for a BRT system in Indianapolis, Indiana. Over 3 million data records during the 3-month period between March and May 2022 are analyzed to develop visualizations and performance metrics. A methodology to estimate the average delay and schedule adherence is presented along a route comprised of 74 signals and 28 bus stations. Additionally, this research demonstrates how these performance measures can be used to evaluate dedicated and non-dedicated bus lanes with general traffic. Travel times and reliability of buses are compared with nearly 30 million private vehicle trips. Results show that median travel time for buses on dedicated bi-directional lanes is within one minute of general traffic and during peak periods the buses are often faster. Schedule adherence was observed to be more challenging, with approximately 3% of buses arriving within 1 minute on average during the 5AM hour and 5% of buses arriving 6 - 9 minutes late during the 5PM hour. The framework and performance measures presented in this research provide agencies and transportation professionals with tools to identify opportunities for adjustments and to justify investment decisions.

Charging Pile Siting Recommendations via the Fusion of Points of Interest and Vehicle Trajectories

By mining of the requirements of lots of electric vehicle users for charging piles, this paper proposes the charging pile siting algorithm via the fusion of Points of Interest and vehicle trajectories. The proposed algorithm computes appropriate charging pile locations by: 1) mining user Points of Interest from social network; 2) mining parking sites of vehicle form GPS trajectories and 3) fusing the Points of Interest and parking sites together then clustering the fusions with our improved DBSCAN algorithm, whose clustering results indicates the final appropriate charging pile locations. Experimental results show that our proposed methods are more efficient than existing methods.

Development and Evaluation of Intersection-Based Turning Movement Counts Framework Using Two Channel LiDAR Sensors

This paper presents vehicle localization and tracking methodology to utilize two-channel LiDAR data for turning movement counts. The proposed methodology uniquely integrates a K-means clustering technique, an inverse sensor model, and a Kalman filter to obtain the final trajectories of an individual vehicle. The objective of applying K-means clustering is to robustly differentiate LiDAR data generated by pedestrians and multiple vehicles to identify their presence in the LiDAR’s field of view (FOV). To localize the detected vehicle, an inverse sensor model was used to calculate the accurate location of the vehicles in the LiDAR’s FOV with a known LiDAR position. A constant velocity model based Kalman filter is defined to utilize the localized vehicle information to construct its trajectory by combining LiDAR data from the consecutive scanning cycles. To test the accuracy of the proposed methodology, the turning movement data was collected from busy intersections located in Newark, NJ. The results show that the proposed method can effectively develop the trajectories of the turning vehicles at the intersections and has an average accuracy of 83.8%. Obtained R-squared value for localizing the vehicles ranges from 0.87 to 0.89. To measure the accuracy of the proposed method, it is compared with previously developed methods that focused on the application of multiple-channel LiDARs. The comparison shows that the proposed methodology utilizes two-channel LiDAR data effectively which has a low resolution of data cluster and can achieve acceptable accuracy compared to multiple-channel LiDARs and therefore can be used as a cost-effective measure for large-scale data collection of smart cities.

A Method of Road Data Aided Inertial Navigation by Using Learning to Rank and ICCP Algorithm

As an independent navigation method,inertial navigation system(INS)has played a huge advantage in a lot of special conditions.But its positioning error will accumulate with time,so it is difficult to work independently for a long time.The vehicle loaded with the inertial navigation system usually drives on the road,so the high precision road data based on geographic information system(GIS)can be used as a bind of auxiliary information,which could correct INS errors by the correlation matching algorithm.The existing road matching methods rely on mathematical models,mostly for global positioning system(GPS)trajectory data,and are limited to model parameters.Therefore,based on the features of inertial navigation trajectory and road,this paper proposes a road data aided vehicle inertial navigation method based on the learning to rank and iterative closest contour point(ICCP)algorithm.Firstly,according to the geometric and directional features of inertial navigation trajectory and road,the combined feature vector is constructed as the input value;Furthermore,the scoring function and RankNet neural network based on the features of vehicle trajectory data and road data are constructed,which can learn and extract the features;Then,the nearest point of each track point and its corresponding road data set to be matched is calculated.The average translation between the two data sets is calculated by using the position relationship between each group of track points to be matched and road points;Finally,the trajectory data set is iteratively translated according to the translation amount,and the matching track point set is obtained when the trajectory error converges to complete the matching.During experiments,it is compared with other algorithms including the hidden Markov model(HMM)matching method.The experimental results show that the algorithm can effectively suppress the divergence of trajectory error.The matching accuracy is close to HMM algorithm,and the computational efficiency can meet the requirements of the traditional matching algorithm.

A review of vehicle speed control strategies

Currently,traffic problems in urban road traffic environments remain severe,traffic pollution and congestion have not been effectively improved,and traffic accidents are still frequent.Traditional traffic signal control methods have little effect on these problems.With the continuous improvement of communication technology and network connections,vehicle speed guidance provides a new idea for solving the above problems and has gradually become a popular topic in academic research.However,its generalization has shortcomings.Therefore,this paper summarizes the research on vehicle speed control strategies in urban road environments and provides suggestions for future research.In this paper,we summarize the existing research in four parts.First,we categorize existing research based on vehicle type.Second,the vehicle speed guidance problem is divided according to the problem research scene.Third,we summarize the existing literature regarding vehicle speed.Finally,we summarize the methods used for speed guidance.Through an analysis of the existing literature,it is concluded that there is a deficiency in the existing research,and suggestions for the future of vehicle speed guidance research are suggested.

Reentry trajectory optimization for hypersonic vehicle satisfying complex constraints

The reentry trajectory optimization for hypersonic vehicle（HV）is a current problem of great interest.Some complex constraints,such as waypoints for reconnaissance and no-fly zones for threat avoidance,are inevitably involved in a global strike mission.Of the many direct methods,Gauss pseudospectral method（GPM）has been demonstrated as an effective tool to solve the trajectory optimization problem with typical constraints.However,a series of diffculties arises for complex constraints,such as the uncertainty of passage time for waypoints and the inaccuracy of approximate trajectory near no-fly zones.The research herein proposes a multi-phase technique based on the GPM to generate an optimal reentry trajectory for HV satisfying waypoint and nofly zone constraints.Three kinds of specifc breaks are introduced to divide the full trajectory into multiple phases.The continuity conditions are presented to ensure a smooth connection between each pair of phases.Numerical examples for reentry trajectory optimization in free-space flight and with complex constraints are used to demonstrate the proposed technique.Simulation results show the feasible application of multi-phase technique in reentry trajectory optimization with waypoint and no-fly zone constraints.

Video-based trajectory extraction with deep learning for High-Granularity Highway Simulation(HIGH-SIM)

High-granularity vehicle trajectory data can help researchers develop traffic simulation models,understand traffic flow characteristics,and thus propose insightful strategies for road traffic management.This paper proposes a novel vehicle trajectory extraction method that can extract high-granularity vehicle trajectories from aerial videos.The proposed method includes video calibration,vehicle detection and tracking,lane marking identification,and vehicle motion characteristics calculation.In particular,the authors propose a Monte-Carlo-based lane marking identification approach to identify each vehicle's lane.This is a challenging problem for vehicle trajectory extraction,especially when the aerial videos are taken from a high altitude.The authors applied the proposed method to extract vehicle trajectories from several high-resolution aerial videos recorded from helicopters.The extracted dataset is named by the High-Granularity Highway Simulation(HIGH-SIM)vehicle trajectory dataset.To demonstrate the effectiveness of the proposed method and understand the quality of the HIGHSIM dataset,we compared the HIGH-SIM dataset with a well-known dataset,the NGSIM US-101 dataset,regarding the accuracy and consistency aspects.The comparison results showed that the HIGH-SIM dataset has more reasonable speed and acceleration distributions than the NGSIM US-101 dataset.Also,the internal and platoon consistencies of the HIGH-SIM dataset give lower errors compared to the NGSIM US-101 dataset.To benefit future research,the authors have published the HIGH-SIM dataset online for public use.

Vehicle Travel Destination Prediction Method Based on Multi-source Data

Research on vehicle travel destinations mostly only consider vehicle trajectory data and ignore the influence of other multi-source data,such as weather,time,and points of interest(POI).This study proposes a destination prediction method based on multi-source data,and a multi-input neural network model is established.In terms of the coding of vehicle trajectory data,a GeoHash to vector(Geo2vec)model is proposed to realize the characterization of the trajectory.As for the coding of temporal features,a cyclic coding model is proposed based on trigonometric functions.For the coding of POI,an origin-destination POI matrix(OD-POI)model is proposed based on the state transition probability.Experimental results show that in terms of the average distance and root-mean-square distance deviations,Geo2vec reveals reductions of 4.51%and 5.63%compared to word to vector(Word2vec),and cyclic encoding shows reductions of 6.35%and 6.67%compared to label encoding;further,the method of OD-POI state transition probability is reduced by 5.85%and 6.4%,and the model based on multi-source data is 17.29%and 17.65%lower than the model based on trajectory data only.Finally,the cyclic encoding is reduced by 48.60%in the data dimension compared to one-hot encoding.Accurate destination prediction will help improve the efficiency of automotive human-computer interaction.

From rectangle to parallelogram:an area-weighted method to make time-space diagrams incorporate traffic waves

A time-space(TS)traffic diagram is one of the most important tools for traffic visualization and analysis.Recently,it has been empirically shown that using parallelogram cells to construct a TS diagram outperforms using rectangular cells due to its incorporation of traffic wave speed.However,it is not realistic to immediately change the fundamental method of TS diagram construction that has been well embedded in various systems.To quickly make the existing TS diagram incorporate traffic wave speed and exhibit more realistic traffic patterns,the paper proposes an area-weighted transformation method that directly transforms rectangular-cell-based TS(rTS)diagrams into parallelogram-cell-based TS(pTS)diagrams,avoiding tracing back the raw data of speed to make the transformation.Two five-hour trajectory datasets from Japanese highway segments are used to demonstrate the effectiveness of the proposed methods.The travel time-based comparison involves assessing the disparities between actual travel times and those computed using rTS diagrams,as well as travel times derived directly from pTS diagrams based on rTS diagrams.The results show that travel times calculated from pTS diagrams converted from rTS diagrams are closer to the actual values,especially in congested conditions,demonstrating superior performance in parallelogram representation.The proposed transformation method has promising prospects for practical applications,making the widely-existing TS diagrams show more realistic traffic patterns.

Real-time trajectory planning for UCAV air-to-surface attack using inverse dynamics optimization method and receding horizon control

This paper presents a computationally efficient real-time trajectory planning framework for typical unmanned combat aerial vehicle （UCAV） performing autonomous air-to-surface （A/S） attack. It combines the benefits of inverse dynamics optimization method and receding horizon optimal control technique. Firstly, the ground attack trajectory planning problem is mathematically formulated as a receding horizon optimal control problem （RHC-OCP）. In particular, an approximate elliptic launch acceptable region （LAR） model is proposed to model the critical weapon delivery constraints. Secondly, a planning algorithm based on inverse dynamics optimization, which has high computational efficiency and good convergence properties, is developed to solve the RHCOCP in real-time. Thirdly, in order to improve robustness and adaptivity in a dynamic and uncer- tain environment, a two-degree-of-freedom （2-DOF） receding horizon control architecture is introduced and a regular real-time update strategy is proposed as well, and the real-time feedback can be achieved and the not-converged situations can be handled. Finally, numerical simulations demon- strate the efficiency of this framework, and the results also show that the presented technique is well suited for real-time implementation in dynamic and uncertain environment.