Interaction-Aware Trajectory Prediction of Connected Vehicles using CNN-LSTM Networks

Mo, Xiaoyu; Xing, Yang

doi:10.1109/iecon43393.2020.9255162

Cited by 56 publications

(44 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional social pooling designs an occupancy grid, where each cell contains the feature of the agent that falls in it, to model the interaction among agents in the grid [13]. The grid representation is modified in [17] to observe only the eight agents that mostly affect the target vehicle's behavior. The grid representation is applicable to highway driving since the highway is almost straight and can be easily divided into a grid.…”

Section: A Interaction Representationmentioning

confidence: 99%

“…II compares the proposed three-channel model HEAT-I-R with existing methods. It shows that: 1) The proposed HEAT-I-R outperforms DESIRE [49] and MultiPath [50], even though these two methods predict multi-modal (MM) trajectories for a single agent and the ADE and FDE are reported with the minimum values among the multiple predictions [22]; 2) HEAT-I-R matches the performance of TNT [22] and ReCoG [17]. Please note that TNT [22] predicts six-modal trajectories for a single agent and reports the minimum ADE and FDE over all predictions and ReCoG [15], the winner solution of the INTERPRET Challenge (NeurIPS 2020) [51], predicts a single trajectory for a single target.…”

Section: A Validation On Heterogeneous Datasetmentioning

confidence: 99%

“…The dataset is constructed by first selecting target vehicles that have changed their lanes only once during recording, then selecting trajectory segments for the target vehicle and its neighboring vehicles. The data processing procedure is similar to that in CNN-LSTM [17], a previous work focusing on the NGSIM dataset, except that an arbitrary number of neighboring vehicles is allowed in this work. After above processing, totally 63, 176 data pieces are selected for training (53,176) and validation (10, 000).…”

Section: B Validation On Homogeneous Datasetmentioning

confidence: 99%

“…IV. The prediction results in this section are evaluated using root-mean-square error (RMSE) in meters to compare with the existing works [13], [17], [23].…”

Section: B Validation On Homogeneous Datasetmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Agent Trajectory Prediction With Heterogeneous Edge-Enhanced Graph Attention Network

Huang

Xing

et al. 2022

IEEE Trans. Intell. Transport. Syst.

Self Cite

139

View full text Add to dashboard Cite

Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for safe and efficient operation of connected automated vehicles under complex driving situations. Two main challenges for this task are to handle the varying number of heterogeneous target agents and jointly consider multiple factors that would affect their future motions. This is because different kinds of agents have different motion patterns, and their behaviors are jointly affected by their individual dynamics, their interactions with surrounding agents, as well as the traffic infrastructures. A trajectory prediction method handling these challenges will benefit the downstream decisionmaking and planning modules of autonomous vehicles.To meet these challenges, we propose a three-channel framework together with a novel Heterogeneous Edge-enhanced graph ATtention network (HEAT). Our framework is able to deal with the heterogeneity of the target agents and traffic participants involved. Specifically, agents' dynamics are extracted from their historical states using type-specific encoders. The inter-agent interactions are represented with a directed edgefeatured heterogeneous graph and processed by the designed HEAT network to extract interaction features. Besides, the map features are shared across all agents by introducing a selective gate-mechanism. And finally, the trajectories of multiple agents are predicted simultaneously. Validations using both urban and highway driving datasets show that the proposed model can realize simultaneous trajectory predictions for multiple agents under complex traffic situations, and achieve state-of-the-art performance with respect to prediction accuracy. The achieved final displacement error (FDE@3sec) is 0.66 meter under urban driving, demonstrating the feasibility and effectiveness of the proposed approach.

show abstract

Section: A Interaction Representationmentioning

confidence: 99%

Section: A Validation On Heterogeneous Datasetmentioning

confidence: 99%

Section: B Validation On Homogeneous Datasetmentioning

confidence: 99%

“…IV. The prediction results in this section are evaluated using root-mean-square error (RMSE) in meters to compare with the existing works [13], [17], [23].…”

Section: B Validation On Homogeneous Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Agent Trajectory Prediction With Heterogeneous Edge-Enhanced Graph Attention Network

Huang

Xing

et al. 2022

IEEE Trans. Intell. Transport. Syst.

Self Cite

139

View full text Add to dashboard Cite

show abstract

“…e abovementioned models require the input length to be predefined and static, and they cannot automatically determine the optimal time lags. To remedy these problems, many works have been done such as [24] used a model called long short-term memory recurrent neural network (LSTM RNN) that capture the nonlinearity and randomness of traffic flow more effectively and automatically determine the optimal time lags; [25] presented a novel long short-term memory neural network to predict travel speed using microwave detector data, where the future traffic condition is commonly relevant to the previous events with long time spans; Mo et al [26] predicted the future trajectory of a surrounding vehicle in congested traffic by using the CNN-LSTM. To the best of our knowledge, no work is found in the literature on car-sharing time series prediction using CNN-LSTM.…”

Section: Literature Reviewmentioning

confidence: 99%

Modelling on Car‐Sharing Serial Prediction Based on Machine Learning and Deep Learning

et al. 2022

View full text Add to dashboard Cite

The car-sharing system is a popular rental model for cars in shared use. It has become particularly attractive due to its flexibility; that is, the car can be rented and returned anywhere within one of the authorized parking slots. The main objective of this research work is to predict the car usage in parking stations and to investigate the factors that help to improve the prediction. Thus, new strategies can be designed to make more cars on the road and fewer in the parking stations. To achieve that, various machine learning models, namely vector autoregression (VAR), support vector regression (SVR), eXtreme gradient boosting (XGBoost), k-nearest neighbors (kNN), and deep learning models specifically long short-time memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN), CNN-LSTM, and multilayer perceptron (MLP), were performed on different kinds of features. These features include the past usage levels, Chongqing’s environmental conditions, and temporal information. After comparing the obtained results using different metrics, we found that CNN-LSTM outperformed other methods to predict the future car usage. Meanwhile, the model using all the different feature categories results in the most precise prediction than any of the models using one feature category at a time

show abstract

Strip and Spatial Social Pooling for Trajectory Prediction

Chen¹,

Li²,

Xiao³

et al. 2023

Proceedings of the World Conference on Intelligent and 3-D Technologies (WCI3DT 2022)

View full text Add to dashboard Cite

Interaction-Aware Trajectory Prediction of Connected Vehicles using CNN-LSTM Networks

Cited by 56 publications

References 18 publications

Multi-Agent Trajectory Prediction With Heterogeneous Edge-Enhanced Graph Attention Network

Multi-Agent Trajectory Prediction With Heterogeneous Edge-Enhanced Graph Attention Network

Modelling on Car‐Sharing Serial Prediction Based on Machine Learning and Deep Learning

Strip and Spatial Social Pooling for Trajectory Prediction

Contact Info

Product

Resources

About