Vehicle Trajectory Research Articles

Trajectory prediction based on the dynamic characteristics and coupling relationships among vehicles in highway scenarios

In dynamic and highly interactive traffic scenarios, vehicle trajectory prediction has become a critical and complex problem in vehicle assistance systems due to the uncertainty of traffic participant behaviour. This study proposes a novel vehicle trajectory prediction method called the Dynamic Coupling-based Long and Short-Term Memory Network (DSKM-LSTM). The method innovatively combines a vehicle dynamics model with the dynamic coupling between vehicles by integrating the intrinsic motion laws of the vehicles with the correlation of the motion parameters (position, velocity, and acceleration) between the vehicles via Kalman filtering. Subsequently, this information is embedded into a Long Short-Term Memory (LSTM)-based encoder-decoder framework to encode and decode historical trajectories with the fused information in order to predict future driving trajectories. Additionally, this paper introduces a dynamic loss function that optimizes the generalization capability and iteration time of DSKM-LSTM by adjusting the threshold value in real time and dynamically updating the loss value. This approach effectively addresses the problem of insufficient objectivity and accuracy in existing vehicle trajectory prediction models and provides a theoretical foundation for generating objective and interpretable trajectories in the field of trajectory prediction. Validation results on three publicly available datasets show that DSKM-LSTM achieves efficient and accurate long-term (5-s) trajectory prediction in complex traffic scenarios (e.g., motorways).

Adaptive Time-Varying Formation Maneuvering Control for Multi-Robot Systems in Complex Obstacle-Rich Environments

To tackle the challenge of time-varying formation control for underactuated robots under model parameter uncertainties and environmental disturbances, this study proposes an affine formation control approach enhanced by an Extended State Observer. Initially, using affine positioning theory and polynomial interpolation, guidelines for selecting leader vehicles and trajectory planning methods are established, whereby the trajectory of follower vehicles is uniquely determined through the stress matrix. To address the cumulative disturbances arising from model uncertainties and environmental factors impacting the formation, an Extended State Observer with optimized parameters is introduced. Furthermore, a distributed affine formation control method with disturbance rejection is designed specifically for underactuated robots with “nonlinear, strongly coupled” dynamics, ensuring that the formation system can track the target configuration within bounded error margins. Finally, theoretical analysis and simulation outcomes ultimately confirm the efficacy of the control approach in achieving resilient formation tracking.

Vehicle trajectory dataset from drone videos including off-ramp and congested traffic – Analysis of data quality, traffic flow, and accident risk

Vehicle trajectory data have become essential for many research fields, such as traffic flow, traffic safety, and automated driving. To make trajectory data useable for researchers, an overview of the included road section and traffic situation as well as a description of the data processing methodology is necessary. In this paper, we present a trajectory dataset from a German highway with two lanes per direction, an off-ramp and congested traffic in one direction, and an on-ramp in the other direction. The dataset contains 8,648 trajectories and covers 87 ​min and an ∼1,200 ​m long section of the road. The trajectories were extracted from drone videos using a posttrained YOLOv5 object detection model and projected onto the road surface via three-dimensional (3D) camera calibration. The postprocessing methodology can compensate for most false detections and yield accurate speeds and accelerations. The trajectory data are also compared with induction loop data and vehicle-based smartphone sensor data to evaluate the plausibility and quality of the trajectory data. The deviations of the speeds and accelerations are estimated at 0.45 ​m/s and 0.3 ​m/s2, respectively. We also present some applications of the data, including traffic flow analysis and accident risk analysis.

Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTM

Quantifying and predicting driving risks for connected autonomous vehicles (CAVs) is critical to ensuring the safe operation of traffic in complex environments. This study first establishes a car-following model for CAVs based on molecular force fields. Subsequently, using a convolutional neural network and long short-term Memory (CNN-LSTM) deep-learning model, the future trajectory of the target vehicle is predicted. Risk is quantified by employing models that assess both the collision probability and collision severity, with deep-learning techniques applied for risk classification. Finally, the High-D dataset is used to predict the vehicle trajectory, from which the speed and acceleration of a target vehicle are derived to forecast driving risks. The results indicate that the CNN-LSTM model, when compared with standalone CNN and LSTM models, demonstrates a superior generalization performance, a higher sensitivity to risk changes, and an accuracy rate exceeding 86% for medium- and high-risk predictions. This improved accuracy and efficacy contribute to enhancing the overall safety of connected vehicle platoons.

Kernel-Based Metrics Learning for Uncertain Opponent Vehicle Trajectory Prediction in Autonomous Racing

Kernel-Based Metrics Learning for Uncertain Opponent Vehicle Trajectory Prediction in Autonomous Racing

Developing and validating an adaptive multi-layer vehicle trajectory reconstruction method for outlier removal

Trajectory data is vital for traffic flow studies, and aerial photography-based methods are increasingly used to collect such data. However, these datasets often contain errors from various sources, which can be exacerbated by numerical derivative processes. Previous efforts have not fully addressed some of these issues such as consistency, varying length of outlier sequences, and unknown ground truth trends. Moreover, existing validation methods are often indirect and problematic. To address these limitations, we propose an adaptive multi-layer vehicle trajectory reconstruction method, which consists of three modules: the Initial Window Arrangement module to ensure the precise alignment between the reconstruction window and detected outlier fragments, maintaining internal consistency at boundary points; the Window Size Feasibility Test module to adaptively determine the window size according to varying length of outlier sequences, and XGBoost-based Ground Truth Estimation module to be combined with a least-square-based objective function to significantly improve reconstruction accuracy and more closely replicate the underlying trend. Additionally, we introduce the jerk-based reconstruction, which outperforms the acceleration-based reconstruction. To reliably assess and select the best ground truth estimation scheme and objective function, a novel synthetic dataset containing both the ground truth and realistic outlier fragments is proposed. Subsequently, a comparative evaluation of six different outlier removal methods was conducted using Zen Traffic Data. The validation results, utilizing both the synthetic dataset and Zen Traffic Data, demonstrate the exceptional performance of the proposed method across various evaluation perspectives. The good performance of the proposed outlier removal method is further demonstrated by comparing the IDM calibration results using the trajectories with and without outliers being removed. With just one parameter (jerk anomaly threshold), the parameter settings of our method are more objective and generalizable.

Multicolumn Self-Attention GRU Model for Intersection Vehicle Trajectory Prediction

Multicolumn Self-Attention GRU Model for Intersection Vehicle Trajectory Prediction

Trajectory and Motion Prediction of Autonomous Vehicles Driving Assistant System using Distributed Discriminator Based Bi-Directional Long Short Term Memory Model

Trajectory and Motion Prediction of Autonomous Vehicles Driving Assistant System using Distributed Discriminator Based Bi-Directional Long Short Term Memory Model

An explicit discrete-time dynamic vehicle model with assured numerical stability

Numerical stability is of great significance for discrete-time dynamic vehicle model. Among the unstable factors, low-speed singularity stands out as one of the most challenging issues, which arises from that the denominator of tire side angle term only contains the vehicle longitudinal speed. Consequently, for the common low-speed and stop-start driving scenarios, the calculated tire slip angle will approach infinity, which will further lead to the numerical explosion of other vehicle states. In response to this critical challenge, we propose a discrete-time dynamic vehicle model that effectively mitigates the low-speed singularity issue, ensuring numerical stability and maintaining the explicit form – highly favoured by model-based control algorithms. To validate the numerical stability of our model, we conduct a rigorous theoretical analysis, establishing sufficient conditions for stability, and conduct extensive empirical validation tests across a wide spectrum of speeds. Subsequent to the validation process, we conduct comprehensive simulations comparing our proposed model with both kinematic models and existing dynamic models discretised through the forward Euler method. The results demonstrate that our proposed model shows better comprehensive performance in terms of both the accuracy and numerical stability. Finally, the real vehicle experiments are carried out to support that our proposed model can closely aligns to the real vehicle trajectories showcasing its practicality and ease of use. Notably, our work stands as the pioneering endeavour in introducing an explicit discrete-time dynamic vehicle model suitable for common urban driving scenarios including low-speed and stop-start.

Research on intelligent computing model of aerodynamic fusion 6-DOF trajectory and attitude of low-orbit vehicle

Research on intelligent computing model of aerodynamic fusion 6-DOF trajectory and attitude of low-orbit vehicle

A hierarchical intersection system control framework in mixed traffic conditions

Signalized intersections play a crucial role in urban road system and are a significant source of vehicle delays. Conventional intersection control methods struggle to cope with increasingly challenging traffic conditions. Fortunately, the development of artificial intelligence(AI), information communication technology(ICT) and connected and automated vehicle(CAV) technologies has brought new opportunities to enhance traffic performance at intersections. Based on these technologies, in the mixed traffic environment of CAVs and connected human-driven vehicles (CHVs), this paper proposes a hierarchical intersection system control framework, which adopts intersection level distributed control and corridor level centralized control. At the intersection level, considering the impact of CAV-dedicated lanes and using the CAV platoon and “1 + n” platoon consisting of one leading CAV and n following CHVs as control units, the mixed integer quadratic programming problem and optimal control problem are formulated to collaboratively optimize signal timing, lane settings and vehicle trajectories at isolated signalized intersections. At the corridor level, based on the optimization results of the intersection level and the critical path information, the critical path performance function and multi-stage optimal trajectory control formula are constructed to optimize the signal offsets and vehicle trajectories, which are passed to the intersection level, and ultimately minimize vehicle delays in the corridor. Simulation experiments and sensitivity analysis demonstrate the effectiveness and stability of the proposed framework in reducing vehicle delay and improving fuel consumption.

Flight trajectory optimization study of a variable-cycle turbine-based combined cycle engine hypersonic vehicle based on airframe/engine integration

Abstract To investigate the optimal flight trajectory for hypersonic vehicle and Turbine-Based Combined Cycle (TBCC) engine to enhance mission efficacy, a performance calculation model of a variable-cycle TBCC engine is developed utilizing the method of airframe/engine integrated performance analysis. Employing the Radau pseudospectral method for trajectory optimization, the study of the hypersonic vehicle involves the angle of attack, the scramjet engine equivalence ratio, and the core driven fan stage (CDFS) stator vane angle as control variables. Two optimization scenarios were considered: minimizing climb time and maximizing range. The findings indicate that by optimally adjusting the angle of attack and the scramjet engine’s equivalence ratio, the vehicle’s climb time can be reduced by up to 33.68 %, and the total flight duration by 8.07 %. Moreover, optimizing these variables, along with CDFS stator vane angle, can decrease fuel consumption during climb and potentially extend cruising distance by 8.56 %, increasing overall range by 3.63 %.

Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction

This paper analyzes the rounD dataset to advance motion forecasting algorithms for autonomous vehicles navigating complex roundabout environments. We develop a trajectory prediction framework inspired by Gated Recurrent Unit (GRU) networks and graph-based modules to effectively model vehicle interactions. Our primary objective is to evaluate the generalizability of the proposed model across diverse training and testing datasets. Through extensive experiments, we investigate how varying data distributions—such as different road configurations and recording times—impact the model’s prediction accuracy and robustness. This study provides key insights into the challenges of domain generalization in autonomous vehicle trajectory prediction.

ASTNAT: an attention-based spatial–temporal non-autoregressive transformer network for vehicle trajectory prediction

ASTNAT: an attention-based spatial–temporal non-autoregressive transformer network for vehicle trajectory prediction

Traffic safety improvement method for highway tunnel entrances based on linear guiding − An engineering practice from China

To improve traffic safety at the entrance of highway tunnels, a comparative analysis of the traffic environment inside and outside the tunnel was conducted, and an improvement scheme based on “linear visual guiding” was developed by considering the human factors. Before and after the improvement of nine experimental tunnels, two batches of vehicle experiments were conducted to analyze the improvement effect of linear guiding scheme on traffic safety. The results show that the linear guiding scheme warns drivers and enables them to make preparations to enter the tunnel earlier. After improvement, the starting position for deceleration (SPD) was 61% earlier and the length of the deceleration section (LDS) has increased by 42%; the starting position for trajectory change (SPTC) was 153% earlier and the length of the trajectory change section (LTCS) has increased by 44%. The improved deceleration and trajectory change are earlier and smoother, and the dramatic changes in speed and trajectory in the tunnel entrance are resolved. When entering the tunnel, drivers sequentially complete deceleration, vehicle trajectory adjustment, and visual adaptation to black-hole effect, disperses driving tasks, reducing the coupling of driving risks. And use linear guiding facilities to enhance the local brightness of the tunnel, enhancing the driver’s visual perception ability in the black-hole effect area. Linear guiding scheme has good results during day, night, and fog, and is able to improve traffic safety at tunnel entrances in all-weather and multiple time periods.

Study on Intelligent Vehicle Trajectory Planning and Tracking Control Based on Improved APF and MPC

Study on Intelligent Vehicle Trajectory Planning and Tracking Control Based on Improved APF and MPC

Three-Dimensional Unmanned Aerial Vehicle Trajectory Planning Based on the Improved Whale Optimization Algorithm

Three-Dimensional Unmanned Aerial Vehicle Trajectory Planning Based on the Improved Whale Optimization Algorithm

Safety-aware human-lead vehicle platooning by proactively reacting to uncertain human behaving

Human-Lead Cooperative Adaptive Cruise Control (HL-CACC) is regarded as a promising vehicle platooning technology in real-world implementation. By utilizing a Human-driven Vehicle (HV) as the platoon leader, HL-CACC reduces the cost and enhances the reliability of perception and decision-making. However, state-of-the-art HL-CACC technology still has a great limitation on driving safety due to the lack of considering the leading human driver’s uncertain behavior. In this study, a HL-CACC controller is designed based on Stochastic Model Predictive Control (SMPC). It is enabled to predict the driving intention of the leading Connected Human-Driven Vehicle (CHV). The proposed controller has the following features: (i) enhanced perceived safety in oscillating traffic; (ii) guaranteed safety against hard brakes; (iii) computational efficiency for real-time implementation. The proposed controller is evaluated on a PreScan&Simulink simulation platform. Real vehicle trajectory data is collected for the calibration of the simulation. Results reveal that the proposed controller: (i) improves perceived safety by 19.17 % in oscillating traffic; (ii) enhances actual safety by 7.76 % against hard brakes; (iii) is confirmed with string stability. The computation time is approximately 3.2 ms when running on a laptop equipped with an Intel i5-13500H CPU. This indicates the proposed controller is ready for real-time implementation.

Investigating a Toolchain from Trajectory Recording to Resimulation

The growing variety of transportation options and increasing traffic congestion pose new challenges for road safety. As a result, there is an intensified focus on developing automated driving features and assistance systems aimed at minimizing accidents caused by human errors. The creation of these systems requires a substantial amount of testing kilometers, with estimates suggesting that around 2.1 billion kilometers would be necessary to ensure that each situation pertinent to the driving function is encountered at least once with a probability of 50%. This paper advances the microscopic simulation of traffic scenarios beyond linear patterns, utilizing the open-source environment openPASS. It addresses the research question of whether existing microscopic simulations are able to realistically represent non-linear traffic scenarios. A comprehensive toolchain integrates simulation with video recordings and laser scans. The study compares recorded traffic flow data with simulations at a T-junction, assessing the realism of vehicle models and trajectory representation. Three scenarios are analyzed, considering vehicles and pedestrians. The 3D geometry of the scene was captured with a laser scanner, enabling the mapping of recorded video data onto a geo-referenced environment. Object trajectories were extracted using an ’Regions with Convolutional Neural Networks features’ object detector. While openPASS simulated vehicle and pedestrian behaviors effectively, limitations in trajectory variability and reaction times were observed. These findings highlight the need for more realistic behavior models. This research emphasizes the necessity for improvements to accommodate complex driving behaviors and pedestrian dynamics.

Failed lane-changing detection and prediction using naturalistic vehicle trajectories

Lane-changing maneuvers are crucial driving behaviors closely linked to various collisions, such as rear-end and sideswipe collisions. Precisely predicting lane-changing maneuvers can aid drivers in making informed decisions, thus enhancing driving safety. However, existing research primarily focuses on successful lane-changing maneuvers, neglecting failed ones. This study comprehensively investigates the detection and prediction of failed lane-changing maneuvers in discretionary scenarios using naturalistic vehicle trajectory data. The Mexican hat wavelet (MHW) is employed to accurately detect key time points in successful or failed lane-changing events, including the start, occurrence of failure, and end of the lane-changing maneuver. Subsequently, a failed lane-changing prediction model based on GA-XGBoost is developed to proactively perceive whether a lane-changing maneuver will succeed before it initiates. Moreover, the Shapley Additive exPlanations (SHAP) technique assesses feature importance and interaction effects between features in the prediction model. The results demonstrate that MHW effectively identifies critical time points in lane-changing events. The proposed GA-XGBoost model achieves an impressive 94.55% accuracy in predicting failed lane-changing maneuvers before the driver initiates the lane-changing maneuver. SHAP values reveal that failed lane-changing maneuvers often result from a high collision risk between the subject vehicle (SV) and the following vehicle in the target lane (FVT). Consequently, drivers should pay increased attention to approaching vehicles from behind. Moreover, accelerating during lane-changing helps maintain a safe distance from FVT, improving the likelihood of a successful lane-changing. Integrating the proposed model into advanced driver-assistance systems or autonomous driving systems has the potential to significantly enhance driving safety.