Trajectories Of Moving Vehicles Research Articles

A multi-modal spatial–temporal model for accurate motion forecasting with visual fusion

The multi-source visual information from ring cameras and stereo cameras provides a direct observation of the road, traffic conditions, and vehicle behavior. However, relying solely on visual information may not provide a complete environmental understanding. It is crucial for intelligent transportation systems to effectively utilize multi-source, multi-modal data to accurately predict the future motion trajectory of vehicles accurately. Therefore, this paper presents a new model for predicting multi-modal trajectories by integrating multi-source visual feature. A spatial–temporal cross attention fusion module is developed to capture the spatiotemporal interactions among vehicles, while leveraging the road’s geographic structure to improve prediction accuracy. The experimental results on the realistic dataset Argoverse 2 demonstrate that, in comparison to other methods, ours improves the metrics of minADE (Minimum Average Displacement Error), minFDE (Minimum Final Displacement Error), and MR (Miss Rate) by 1.08%, 3.15%, and 2.14% , respectively, in unimodal prediction. In multimodal prediction, the improvements are 5.47%, 4.46%, and 6.50%. Our method effectively captures the temporal and spatial characteristics of vehicle movement trajectories, making it suitable for autonomous driving applications.

Vehicle motion trajectory prediction fusion algorithm with driver adventurousness correction factor based on CS-LSTM

Predicting the trajectories of adjacent vehicles plays an important role in the driving safety of adaptive cruise control system. It affects the safety and stability of the vehicle following the target vehicle during the vehicle cruising driving vehicle. However, due to the uncertainty of vehicle dynamics, driver character, and the complexity of the surrounding environment, vehicle trajectory prediction faces great challenges. Hence, a dynamic vehicle trajectory prediction system is proposed based on identifying driver intentions. First, based on a convolution LSTM, the driver adventurousness factor is introduced to describe the driver’s lane-change behavior heterogeneity and improve the accuracy of long-term lane-change trajectory prediction of adjacent lane vehicles. Second, the trajectory prototype predicted trajectory is updated by adjusting the minimum value function until the vehicle model corresponds to the planned sampling trajectory to improve the accuracy of the adjacent lane vehicle’s short-term lane-change trajectory prediction. Finally, the trajectories are fused using the trigonometric fusion algorithm, and the optimal trajectory is the output. The suggested strategy can predict lane-change intentions 2–5 s in advance. The prediction accuracy of the lane-change trajectory was approximately 21% higher than the normal prediction outcomes. The proposed method can be used to improve passenger comfort and the stability of a vehicle following a target vehicle that is separated from the adjacent lane vehicle.

Evaluation of autonomous underwater vehicle motion trajectory optimization algorithms

The operation of autonomous underwater vehicles (AUVs) relies on three major motions: yaw, theta, and depth, each requiring its own set of proportional integral derivative (PID) controller gain criteria. Thus, different issues arise, including the availability of multiple criteria for optimization algorithm evaluation, the importance of these criteria, the trade-off between criterion performance, and criterion critical values. These issues make the evaluation of optimization algorithms for AUV motion control a complex multicriteria decision-making (MCDM) problem. This research proposes a novel selection-integrated approach for AUV optimization algorithms in different motions using two MCDM methods: fuzzy-weighted zero-inconsistency (FWZIC) for criteria weighting and fuzzy decision by opinion score method (FDOSM) for optimization algorithm selection. The approach comprises three main phases: development of PID, FWZIC-based criteria weighting, and FDOSM-based optimization algorithm selection. In all three motion types – “depth”, “yaw”, and “theta” – Kp_θ had the highest weight value, with respective weights of 0.143, 0.149, and 0.142. In contrast, Ki_depth consistently received the lowest weight value across all three motion types, with respective weights of 0.057, 0.0598, and 0.057. Regarding the “depth” motion, the Archimedes optimization algorithm (AOA) was the highest-performing alternative with a score of 0.077, while the eagle strategy–particle swarm optimization algorithm was the worst alternative with a score of 0.022. The Cuckoo optimization algorithm was identified as the best alternative for the “yaw” motion with a score of 0.072, whereas black hole optimization had the lowest score of 0.036. The best alternative for the “theta” motion was AOA with a score of 0.067, and the worst algorithm was sunflower optimization with a score of 0.028. This developed approach was evaluated based on systematic ranking and sensitivity analysis, which confirmed the validity of the proposed work.

Vehicle Trajectory Prediction Method Based on “Current” Statistical Model and Cubature Kalman Filter

Vehicle motion trajectory prediction is the basis of vehicle collision early warning or vehicle conflict resolution. In order to improve the accuracy of trajectory prediction, a vehicle trajectory prediction method based on “current” statistical (CS) model and cubature Kalman filter (CKF) is proposed. This method considers the acceleration variation rules in the actual motion process of the vehicle in the state equation, so that the estimated value of the acceleration can be consistent with the real range. This condition overcomes the limitation of the general trajectory prediction model, which ignores the acceleration change, so it improved prediction accuracy. In addition, this method also avoids the large amount of computational resources required, being that some new methods describe the real acceleration fluctuations. The vehicle trajectory at the intersection that crossed by Yingbin Avenue and Qiche Avenue in Nanchang is selected to verify the tracking performance of Constant Acceleration-Unscented Kalman Filter (CA-UKF), Current Statistical-Unscented Kalman Filter (CS-UKF), and CS-CKF models. The results show that the CS-CKF model has superior prediction effectiveness than the CA-UKF and CS-UKF models, and it improves the accuracy of vehicle motion trajectory prediction.

Reconstruction of incomplete public transportation check-out records by heuristic approaching

Smart cards, integrated circuit cards, are frequently used to pay transportation fees in many countries such as the United States, the European Union, Korea and others. Smart card transaction histories in public transportation have been used in making diverse traffic policies. Unfortunately, data preprocessing is required to organize records to extract useful information since the raw data contain artifacts and incomplete information. The paired data, i.e. a boarding and its associated alighting, are one of the key pieces of information required to yield the city traffic demand. However, it is difficult to gather the paired data mainly because the card tagging policies and data collecting methods vary from city to city and from institution to institution. The broken trip links between the boarding and its associated alighting information are the most frequent incomplete data in the smart card histories. Although huge budgets are spent on annual traffic surveys in many countries, there are no accurate Smart card data analysis methods that cover all city cases due to high data complexity and limited base information. Among these two restrictions, limited information is more difficult to resolve because it has a large codomain, thousands of stops, for inference under tiny samples. It gives handicaps of applying well-known high-performance approaches such as deep learning and probability analysis. We propose a reconstruction method by a customized clustering algorithm based on coordinates of transactions-occurred stops, user trip histories and actual vehicle movement trajectories for incomplete trip pairs. The proposed method is derived from evaluating each passenger’s historical clusters and trip patterns. In a blind test 79.1% accuracy is achieved in predicting missing alighting stops while conventional methods reach only 42.3% accuracy.

Tailored Hidden Markov Model: A Tailored Hidden Markov Model Optimized for Cellular-Based Map Matching

Although the GPS-based positioning is ubiquitous for its high precision, the high power consumption brought by the high sampling frequency and the poor GPS signal penetration limits its availability in locating low-power mobile devices (especially mobile phones). As a promising complement, the cellular-based positioning has attracted great attention since it consumes much less power as well as its higher availability. However, the sparsity of cellular-based data (due to lower sampling rate) and large localization errors make the measurement accuracy becomes the main challenge of the cellular-based positioning. hidden Markov model can well solve the problem of positioning error of GPS data, but it is less accurate when applied to map matching of cellular-base data. Therefore, to improve accuracy, in this article, we propose a novel algorithm called the tailored hidden Markov model (THMM) that is optimized for the cellular-based data. Specifically, the geometric, the topological, and the probabilistic characteristics have been considered and fully exploited in the THMM design. Our proposed schemes are evaluated using real-world motor vehicle movement trajectories collected in Tianjin and the experimental results are encouraging compared with the state-of-the-art algorithms.

Determining the trajectory of the vehicle motion on the basis of the recorded physical quantities describing its dynamics during typical maneuvers in road traffic

The paper compares the results of the vehicle motion trajectory calculations determined on the basis of the recorded waveforms of the acceleration vector and angular velocity components during the double lane change maneuver, taking into account the errors of acceleration sensors reset (zeroing). The differences in the results of the calculations were determined and possible causes of these differences were indicated. The test results indicate that special attention should be paid to zeroing the acceleration sensors, in particular the ay component.

Determining the trajectory of the vehicle motion on the basis of the recorded physical quantities describing its dynamics during double lane change maneuvers

The paper indicated the results of the vehicle motion trajectory calculations determined on the basis of the recorded waveforms of the acceleration vector and angular velocity components during the double lane change maneuver, taking into account the errors of acceleration sensors reset (zeroing). For the sake of simplicity, it was assumed that the zeroing errors apply only to the linear acceleration sensors, while the angular velocity sensors show exact values at the time t = 0 s (when starting the double lane change maneuver). During the analysis of the results of the experimental research, the vehicle kinematics model was used, in which right-handed coordinate systems were used: global and two local coordinate systems. The differences in the results of the calculations were determined and possible causes of these differences were indicated. The test results indicate that special attention should be paid to zeroing the acceleration sensors, in particular the ay component.

Conflict Probability Prediction and Safety Assessment of Straight-Left Traffic Flow at Signalized Intersections

The safety of signalized intersections is of great concern. To allow for an effective evaluation measure on the safety level of intersections, traffic conflict analysis methods are commonly used. However, the existing literature has mainly focused on the statistical prediction of conflicts by using surrogate measurements, among which the spatial-temporal characteristics of the potential conflicts have been less addressed. In addition, most of the relevant studies rely on precise trajectory data, and the results could be limited to engineering applications when real-time/comprehensive trajectory data are not available. To address these issues, this study proposes a SICP (signalized intersection conflict probability) model to predict a straight-left traffic flow conflict with a spatial-temporal distribution in the heat map, which could effectively evaluate the traffic safety of the existing or prebuilt signalized intersections on urban roads. Firstly, the impact of vehicle movement characteristics on traffic conflict at signalized intersections was considered by incorporating the vehicle movement trajectory. Secondly, the signal phase was categorized in several stages (each phase contains switching and nonswitching stages); then, a vehicle-vehicle conflicts probability prediction model was established by integrating both horizontal and vertical arrival probability. Finally, to validate the performance of the proposed model, the measured data were collected from the intersection of Wushan road and Yuehan road in Tianhe District, Guangzhou, China. SSAM（Surrogate Safety Assessment Model）traffic conflict simulation was used to analyze the traffic conflict in the actual data and compared to the SICP model. A case study was conducted to reveal the evolution mechanism of the conflict risk coefficient at the signalized intersection and to estimate the safety status under the various security optimization strategies. The experimental results verified the effectiveness of the SICP model, indicating that the proposed model is effective in evaluating the safety level of existing or prebuilt signalized intersections.

Combined Estimation of the Mutual Position of the Master and Slave Vehicle by Ultrasonic Receivers and Gnss-Module Data

The problem of determining the position of master vehicle when implementing a scenario of robotic vehicle as a part of caravanning driving system is studied. The mentioned scenario is expected the slave vehicle to replicate the motion trajectory of master vehicle represented by human operated vehicle, by another robotic vehicle or by human operator. To provide reliable operation of robotic vehicle within autonomous convoy a reliable and precise assessment of master vehicle position and trajectory regardless of environment is required. Implementation of ultrasonic receivers and emitters within information and measurement complex to determine master-slave vehicle mutual position allows to function at any time of the day inside and outside the premises in the presence of dynamic obstacles, smoke, precipitation, etc. Estimation of position and trajectory of master vehicle is accomplished by means of measuring arrival time of ultrasonic wave emitted by active beacon prior to spatial array of ultrasonic receivers. Similar indirect distance measurement between bacon and each receiver allowed to receive a system of equations to be solved by implementation of Kalman filter with Raugh - Tung - Striebel smoother. Major disadvantage of the approach is 20-meter range, which is enough for complex maneuvering. To increase the range of the complex operation, a combined estimation of the master's position based on measuring data of the spatial array of ultrasonic receivers and the module of global navigation satellite system is proposed.

Neural network model for recognition and classification of types of interactions in road traffic

The article presents neural network for recognition of driving strategies based on interactions between drivers in road traffic. It analyzes the architecture of the model implemented as a self-organizing map (SOM), consisting of a group of neural networks based on radial basis functions (RBF). It is a training model grounded in the biological foundations of artificial neural networks, in which the training set should consist exclusively of input vectors; wherein the network training algorithm adjusts itself the network's weights to obtain consistent output vectors (i.e. to make presenting sufficiently close input vectors result into the same outputs). The article presents the results of using a new generation of the neural network developed by us, which includes an adaptive learning algorithm to reduce the effect of re-training (overfitting) and false recognition, as well as to improve the determination of the boundaries between clusters. The aim of the research is to outline architecture and structure of the neural network model that allows recognizing strategical characteristics of driving and can identify strategies of interactions between vehicles (their drivers) in road traffic as well as identify behavioral patterns This paper considers driving strategies that characterize the interaction of dyads of vehicles (drivers) moving in road traffic. The research results show that the SOM RBF neural networks can recognize and classify types of interactions in road traffic based on modelling of the analysis of vehicle movement trajectories. Experimental results demonstrate the neural networks architecture and networks learning involving 400 iterations of streaming the training data representing 500 possible simulated interaction situations. This paper presents a novel neural network model for recognition of drivers' behaviour patterns and for classification of driving strategies into five general classes: (1) competition strategy, (2) contest strategy, (3) evasion strategy, (4) compromise strategy, and (5) active confrontation strategy. This neural network has demonstrated a high rate of recognition and concise clusterization of similar driving strategies. The key contribution of this paper: it proposes a neural network model based on Kohonen's Self-Organizing Map (SOM) for detecting drivers' behaviours from vehicle movement patterns - driving strategies - instead of monitoring driver's specific activities.

Efficient Trajectory Matching Algorithm Based on Spatial Coordinate Rotation

Trajectory similarity estimation is the key to discover vehicle motion characteristics and trajectory classification, but the calculation of trajectory similarity is slow, and improving the speed of trajectory matching can help to carry out trajectory characteristics mining fast. Therefore, an efficient trajectory matching algorithm based on the rotation of spatial coordinate is proposed. Firstly, the trajectory curve is converted into the mean and variance curve which the number of points is equal to the number of rotations by multiple rotation of the spatial coordinate system. Then, Pearson correlation coefficient and Fréchet distance are used to measure the correlation of the mean and variance curves. Finally, the similarity between the original trajectories is determined indirectly according to the values of four parameters: Fréchet mean, Fréchet var, Pearson mean and Pearson var. Based on the taxi trajectory data of Hangzhou, under different trajectory sampling points and spatial coordinate rotation times, compared trajectory matching accuracy and speed with the traditional Hausdorff trajectory matching algorithm. The several experiments show that the algorithm can improve the trajectory matching speed by 85% on average while ensuring the accuracy of trajectory matching. By constructing a visual analysis system that includes three major modules: a map overview showing the results of trajectory matching, several visual interactive components that explore the differences in trajectory matching results, and a module for selecting trajectory matching parameters, explore the differences in the results of the four trajectory matching methods to help road network researchers to match real driving trajectories and find similar trajectory groups faster.

IMPACT ANALYSIS OF ACCIDENTS ON THE TRAFFIC FLOW BASED ON MASSIVE FLOATING CAR DATA

Abstract. The wide usage of GPS-equipped devices enables the mass recording of vehicle movement trajectories describing the movement behavior of the traffic participants. An important aspect of the road traffic is the impact of anomalies, like accidents, on traffic flow. Accidents are especially important as they contribute to the the aspects of safety and also influence travel time estimations. In this paper, the impact of accidents is determined based on a massive GPS trajectory and accident dataset. Due to the missing precise date of the accidents in the data set used, first, the date of the accident is estimated based on the speed profile at the accident time. Further, the temporal impact of the accident is estimated using the speed profile of the whole day. The approach is applied in an experiment on a one month subset of the datasets. The results show that more than 72% of the accident dates are identified and the impact on the temporal dimension is approximated. Moreover, it can be seen that accidents during the rush hours and on high frequency road types (e.g. motorways, trunks or primaries) have an increasing effect on the impact duration on the traffic flow.

Modeling the Influence of Roundabout Deflection on Its Efficiency as a Noise Abatement Measure

Challenges that emerge in roundabout design are mostly related to space constrictions and provision of appropriate deflection around the central island. This can result in speed profiles on roundabouts that might reduce their potential as a noise abatement measure. Because of this, the impact of a roundabout on noise levels and its applicability as a traffic calming device and a noise abatement measure should be investigated in the early design stage, by modeling noise levels. In this paper, the following hypothesis is tested: vehicle movement trajectories, defined during the fastest path performance check in roundabout early design phase, can be used as the road traffic noise sources when modeling noise at roundabouts using static noise model. This procedure (1) simplifies the preparation of the noise model, (2) results in a model that is closer to the real-world in terms of traffic flow conditions, (3) allows the noise calculations in the early stages of roundabout design, and (4) includes the influence of roundabout deflection on calculated noise levels. The abovementioned simplifications of the road traffic noise modeling process should encourage the optimization of roundabout geometry in terms of its noise reduction capabilities in the preliminary design phase of these intersections.

Data Mining Method of Sequential Patterns for Vehicle Trajectory Prediction in VANET

In order to provide the future direction of vehicle flow for travelers, it is necessary to predict the driving trajectory of vehicles running on the road in a certain segments. According to the characteristics of vehicle sequential pattern, the topology of vehicular ad hoc network (VANET) is linked to the real road vehicle movement trajectory. Some new definitions related to sequential patterns in VANET environment are proposed. Based on RSU and V2V schemes, a vehicle movement database is established, and sequential pattern data mining is carried out. Afterward, their communication overhead is evaluated. The support and confidence of the movement rules generated by vehicle routing patterns are calculated to extract the probability of frequent driving trajectories.

Optimizing Geometric Design of Standard Turboroundabouts

Previous studies have shown that existing turboroundabout design procedures, in which swept path analyses are conducted at the end of design process, contain certain disadvantages and understatements which can lead to oversized or undersized turboroundabout solutions i.e. low intersection capacity, poor traffic safety, low driving comfort and high construction costs. Within the scope of this study elements of standard turboroundabouts were designed in accordance with the design vehicle movement trajectories obtained by the swept path analyses. Reliability of the software used in these analyses was verified by the real drives at the test site. Geometric design of standard turboroundabouts was conducted with variation of following influential parameters: design vehicle; circulatory roadway radii; approach leg offset and angle value. Design approach applied in this research resulted in optimal intersection design regarding the occupation of surrounding area and the design vehicle swept path requirements. Circulatory roadway radii and approach leg offset and angle limit values applicable on this intersection type are determined, taking into account the real traffic situation. Additional practical contribution of this research lies in the ability of application of research results in revision of existing guidelines for the design of turboroundabouts, as well as in development of new guidelines in countries which still do not have their own regulations on the design of this rather new multilane roundabout type.

Trajectory control for tire burst vehicle using the standalone and roll interconnected active suspensions with safety-comfort control strategy

The lateral pulling of tire burst vehicle results in accident and fatality on the highway due to its sudden C.G displacement of the vehicle. Improper steering input leads to detach wheel from vehicle and rollover accident due to the weight transfer towards the flat tire. Therefore, this paper attempts to reduce the lateral velocity and its displacement of the vehicle by producing the force through suspension actuator within the suspension limitation and without affecting the steering characteristics. For the analysis, 4-axle truck with velocity controller and steering system incorporated model was built in AMESim environment, which is exported into Matlab/Simulink for the co-simulation. Hydraulic control valve integrated standalone and roll interconnected active suspension scheme’s state space model was identified in Matlab through simple identification method for the comfort and safety MPC controller design. Finally, the results of passive system with Anti-roll bar (ARB) and without ARB, passive and active roll interconnected suspensions, comfort and coordinated control standalone active suspension system are comprised to illustrate the effectiveness and its control strategy. In addition, this work showcased the motion trajectory of vehicle with a flat tire on running over highway with and without steer maneuver.

Surrogate safety indicator for unsignalised pedestrian crossings

ProblemAlthough the road safety situation in Poland is generally improving, the number of accidents at pedestrian crossings has not decreased in the last four years. This paper presents the results of the MOBIS research project, the aim of which was to develop surrogate safety indicators, based on detection of pedestrian-vehicle conflicts using video analysis. MethodPedestrian and vehicle traffic was filmed at two unsignalised pedestrian zebra crossings in Warsaw and Wrocław for over 40 days. Motion trajectories of vehicles and pedestrians were determined based on video processing. Several variables describing pedestrian-vehicle interactions were calculated, such as speed, post-encroachment time, distance between the participants, decelerations, etc. Classification of encounters was based on interactions of pedestrians and vehicles i.e. drivers yielding to pedestrians, vehicles passing just in front of, or behind pedestrians. Results and discussionCriteria for identification of dangerous encounters were selected with the assumption that it should be possible to automate the assessment process. The selected variables were: pedestrian-vehicle passing distance and the vehicle speed at that moment. Other criteria were used in cases of abrupt braking – deceleration exceeding 4 m/s2 and vehicle speed. A Dangerous Encounter Index is proposed as a surrogate safety indicator for pedestrian crossings. It relates the occurrence of dangerous events to exposure, defined as the number of pedestrian-vehicle encounters. Practical applicationsThe proposed index shows that crossing two lanes involves more risk than crossing one lane, given similar traffic flow. Some improvement of safety at both types of crossing was observed after active signage involving blinking lights had been introduced. The proposed method is a step towards automation of safety assessment.

Research project BRIK: development of an innovative method for determining the precise trajectory of a railway vehicle

In the paper the essential assumptions regarding a research project implemented by a consortium of Gdansk University of Technology and Gdynia Maritime University are presented. The project has been commissioned by National Center of Research and Development with cooperation with Polish Railways (PKP Polskie Linie Kolejowe S.A.). The project is focused in implementation of modern measurement techniques using Global Navigation Positioning System GNSS, Inertial Navigation System INS and Mobile Laser Scanning MLS in a railway network management process. The precise aim of the research is both determine geometric parameters of a railway geometric layout as well as a railway vehicle movement trajectory. For this reason the innovative technique of mobile satellite measurements will be used. In the paper a synthetic description of the project together with the particular stages are presented. Also, a part of research which was realized in 2018 is shown. In the first stage, Gdansk University of Technology made a research of existing common methods for determining and assessing a track alignment, presented an idea of mobile investigation of track axis by the use of satellite measurements, took into consideration an issue of influence of dynamic behavior of the measurement vehicle on the accuracy of determined track positions by the use of GNSS/INS techniques and finally presented a technical project of measurement platform. Gdynia Maritime University made a query of GNSS/INS/MLS in measurements of track alignment, elaborated a scheme of measurement devices placement on the mobile measurement platform and studied possibilities of increasing accuracy for estimation a railway vehicle localization in relation to common techniques used by polish train operators.

Planning of driverless vehicle motion trajectory taking into account its dimensional characteristics and under conditions of dynamically changing environment

This paper presents the solution for the task of the planning of the driverless vehicle (DV) driving trajectory for the modern road conditions. The rapidly-exploring random trees (RRT) algorithm consisting in the generation of the treetops under the equiprobability law and search for an optimum trajectory was used as a base. The minimum length acts as a criterion of optimality. The condition for the trajectory generation using the road map model is added to the new algorithm. Thereby, the problem of low processing (response) speed of the optimum trajectory search algorithm was solved.