An Interacting Multiple Model Approach for Target Intent Estimation at Urban Intersection for Application to Automated Driving Vehicle

Shin, Donghoon; Yi, Subin; Park, Kang-moon; Park, Manbok

doi:10.3390/app10062138

Cited by 12 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When F is linear, we can use the Kalman filter to estimate x t from the noisy measurement. Given the estimated state xt−1 at time step t − 1, the prior estimate of x t is 5 xt|t−1 = Fx t−1 .…”

Section: Appendix a Formulation Of Kalman Filtermentioning

confidence: 99%

Communication Scheduling by Deep Reinforcement Learning for Remote Traffic State Estimation With Bayesian Inference

Peng

Xie

Seco‐Granados³

et al. 2022

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

Traffic awareness is the prerequisite of autonomous driving. Given the limitation of on-board sensors (e.g., precision and price), remote measurement from either infrastructure or other vehicles can improve traffic safety. However, the wireless communication carrying the measurement result undergoes fading, noise and interference and has a certain probability of outage. When the communication fails, the vehicle state can only be predicted by Bayesian filtering with a low precision. Higher communication resource utilization (e.g., transmission power) reduces the outage probability and hence results in an improved estimation precision. The power control subject to an estimate variance constraint is a difficult problem due to the complicated mapping from transmit power to vehicle-state estimate variance. In this paper, we develop an estimator consisting of several Kalman filters (KFs) or extended Kalman filters (EKFs) and an interacting multiple model (IMM) to estimate and predict the vehicle state. We propose to apply deep reinforcement learning (DRL) for the transmit power optimization. In particular, we consider an intersection and a lane-changing scenario and apply proximal policy optimization (PPO) and soft actor-critic (SAC) to train the DRL model. Testing results show satisfactory power control strategies confining estimate variances below given threshold. SAC achieves higher performance compared to PPO.

show abstract

Section: Appendix a Formulation Of Kalman Filtermentioning

confidence: 99%

Communication Scheduling by Deep Reinforcement Learning for Remote Traffic State Estimation With Bayesian Inference

Peng

Xie

Seco‐Granados³

et al. 2022

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…There are two control levels separated within the control processes of the SciL framework. The first control level handles the decision making processes of the individual scenario components, like the vehicle/vehicles under test, the pedestrians, the cyclists or the simulated or real traffic management system [98]- [100]. The higher-level control manages the overall coordination of the traffic scenario, taking into account the critical states of the systems, the corner cases, and the implemented test scenario [101].…”

Section: ) Scil Controlmentioning

confidence: 99%

Next Generation X-in-the-Loop Validation Methodology for Automated Vehicle Systems

Szalay

2021

IEEE Access

View full text Add to dashboard Cite

Testing self-driving vehicles is still a new and immature process; the globally harmonised procedure expected much later. The resource-demanding nature of real-world tests makes it indispensable to develop and improve the efficiency of virtual environment based testing methods. Accordingly, a novel Xin-the-Loop framework is proposed to fully exploit the recent advances in info-communication technologies, vehicle automation, and testing and validation requirements. This methodology real-time connects physical and virtual testing with high correlation while completely blurs the sharp boundaries between them. Measurement results confirm the superior performance of the 5G communication link in providing a stable, real-time connection between the real world and its virtual representation. The live demonstration proved the presented concept at the newly constructed Hungarian proving ground for automated driving. The performed investigation also includes comprehensive benchmarking, focusing on the most up-to-date automotive testing frameworks. The analysis considers the methodologies and techniques applied by the most relevant actors in the automotive testing sector worldwide. Accordingly, the newly developed testing framework is evaluated and validated in light of the state-of-the-art methods used by the automotive industry.INDEX TERMS Automotive proving ground, automated vehicle control, autonomous vehicle, co-simulation, digital twin, mixed-reality testing, scenario-based testing, testing and validation, virtual and mixed reality, V-model, X-in-the-loop testing.

show abstract

“…Model-based methods primarily rely on the vehicle's kinematics model, consider the physical characteristics of the vehicle and environmental factors, and use traditional filtering techniques and optimization technologies like the Bayes' theorem [3], Monte Carlo simulation [4], Hidden Markov Model (HMM) [5], Kalman filters [6], Model Predictive Control (MPC) [7], and so on. Shin et al [8] proposed an urban intersection vehicle trajectory prediction method based on internal modeling and Extended Kalman Filter (EKF), incorporates the target vehicle's kinematics and dynamics model. Xie et al [9] designed an IMM trajectory prediction (IMMTP) algorithm combining Interactive Multiple Model (IMM), Unscented Kalman Filter (UKF), and Deep Belief Network (DBN) to investigate vehicle lane-change intentions on highways, where UKF is used to predict the vehicle's trajectory, and DBN predicts intention with uncertainty.…”

Section: Introductionmentioning

confidence: 99%

An Enhanced Vehicle Trajectory Prediction Model Leveraging LSTM and Social-Attention Mechanisms

Qiao,

Gao,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Accurate trajectory prediction for multiple vehicles in complex social interaction environments is essential for ensuring the safety of autonomous vehicles and improving the quality of their planning and control. The social interactions between vehicles significantly influence their future trajectories. However, traditional trajectory prediction models based on Recurrent Neural Networks (RNN) or Convolutional Neural Networks (CNN) often overlook or simplify these interactions. Although these models may exhibit high performance in short-term predictions, they fail to achieve high prediction accuracy in scenarios with long-term dynamic interactions. To address this limitation, we propose a Social-Attention Long Short-Term Memory (LSTM) model which predicts the future trajectories of neighboring vehicles and achieves increased accuracy. Our proposed model employs a Social-Pooling layer to effectively capture cooperative behaviors and mutual influences between vehicles. Additionally, we incorporate a self-attention mechanism to weight the inputs and outputs of the Social-Pooling layer, which is significant for assessing the influence between vehicles in different positions. This combination allows our model to take into consideration both the dependencies within the sequence and the social relationships between vehicles, providing a more comprehensive scene understanding. The efficacy of our model is tested on two real-world freeway trajectory datasets, namely NGSIM and HighD. Our model surpasses various baseline methods, exhibiting exceptional accuracy in both prediction and tracking.

show abstract

An Interacting Multiple Model Approach for Target Intent Estimation at Urban Intersection for Application to Automated Driving Vehicle

Cited by 12 publications

References 20 publications

Communication Scheduling by Deep Reinforcement Learning for Remote Traffic State Estimation With Bayesian Inference

Communication Scheduling by Deep Reinforcement Learning for Remote Traffic State Estimation With Bayesian Inference

Next Generation X-in-the-Loop Validation Methodology for Automated Vehicle Systems

An Enhanced Vehicle Trajectory Prediction Model Leveraging LSTM and Social-Attention Mechanisms

Contact Info

Product

Resources

About