Tra2Tra: Trajectory-to-Trajectory Prediction With a Global Social Spatial-Temporal Attentive Neural Network

Xu, Yi; Ren, Dongchun; Li, Mingxia; Chen, Yuehai; Fan, Mingyu; Xia, Huaxia

doi:10.1109/lra.2021.3057326

Cited by 27 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conversely, Wu et al [36] applied the multi-head attention mechanism to capture the complex temporal correlation of each agent independently. More recently, motivated by the fact that the graph convolutional network (GCN) [37] can capture the relative influence and the potential spatial relationships in traffic scenarios, the graph attention network (GAT) [38] has been used in trajectory prediction [39][40][41], extracting the spatial interaction among neighboring agents by assigning different importance to neighbors around the target agent. In this paper, we design a spatial attention layer based on the GAT to extract the social interactions among vehicles and use a temporal attention layer to capture the temporal relationships according to the self-attention mechanism [42].…”

Section: Attention-based Methods For Trajectory Predictionmentioning

confidence: 99%

Spatial-Temporal Attentive LSTM for Vehicle-Trajectory Prediction

Jiang

Gong

et al. 2022

IJGI

View full text Add to dashboard Cite

Vehicle-trajectory prediction is essential for intelligent traffic systems (ITS), as it can help autonomous vehicles to plan a safe and efficient path. However, it is still a challenging task because existing studies have mainly focused on the spatial interactions of adjacent vehicles regardless of the temporal dependencies. In this paper, we propose a spatial-temporal attentive LSTM encoder–decoder model (STAM-LSTM) to predict vehicle trajectories. Specifically, the spatial attention mechanism is used to capture the spatial relationships among neighboring vehicles and then obtain the global spatial feature. Meanwhile, the temporal attention mechanism is designed to distinguish the effects of different historical time steps on future trajectory prediction. In addition, the motion feature of vehicles is extracted to reveal the influence of dynamic information on vehicle-trajectory prediction, and is combined with the local and global spatial features to represent the integrated features of the target vehicle at each historical moment. The experiments were conducted on public highway trajectory datasets—US-101 and I-80 in NGSIM—and the results demonstrate that our model achieves state-of-the-art prediction performance.

show abstract

Section: Attention-based Methods For Trajectory Predictionmentioning

confidence: 99%

Spatial-Temporal Attentive LSTM for Vehicle-Trajectory Prediction

Jiang

Gong

et al. 2022

IJGI

View full text Add to dashboard Cite

show abstract

“…Five state-of-the-art methods are compared with our proposed method under the new setting and the evaluation protocol. Social-STGCNN [50], PECNet [49], RSBG [64], SGCN [62], and Tra2Tra [76]. We also use following four widely-used DA approaches for comparison.…”

Section: Methodsmentioning

confidence: 99%

“…To further demonstrate this challenge, we apply three state-of-the-art methods, Social-STGCNN [50], SGCN [62], Tra2Tra [76] to demonstrate the performance drop when it comes to different trajectory domains. We take ETH as the example, these models are trained on the validation set of ETH and evaluated on the standard testing set of ETH.…”

Section: Source Trajectorymentioning

confidence: 99%

“…where N is the number of pedestrians in the scene, o i obs represents the coordinates of pedestrian i at the last observed frame T obs . This decentralization operation is able to eliminate the effects of scene size differences and is also applied in recent works [76,87]. We refer to o i t = (x i t , y i t ) as the "relative coordinates" for the following graph construction.…”

Section: Spatial-temporal Feature Representationsmentioning

confidence: 99%

“…We compare our proposed model with total 5 trajectory prediction baselines: Social-STGCNN [50], PECNet [49], RSBG [64], SGCN [62], and Tra2Tra [76]. We implemented these baselines with their provided codes: Social-STGCNN 4 , PECNet 5 , SGCN 6 .…”

Section: Implementation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Trajectory Prediction via Transferable GNN

Xu¹,

Wang²,

Wang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Pedestrian trajectory prediction is an essential component in a wide range of AI applications such as autonomous driving and robotics. Existing methods usually assume the training and testing motions follow the same pattern while ignoring the potential distribution differences (e.g., shopping mall and street). This issue results in inevitable performance decrease. To address this issue, we propose a novel Transferable Graph Neural Network (T-GNN) framework, which jointly conducts trajectory prediction as well as domain alignment in a unified framework. Specifically, a domain-invariant GNN is proposed to explore the structural motion knowledge where the domain-specific knowledge is reduced. Moreover, an attention-based adaptive knowledge learning module is further proposed to explore finegrained individual-level feature representations for knowledge transfer. By this way, disparities across different trajectory domains will be better alleviated. More challenging while practical trajectory prediction experiments are designed, and the experimental results verify the superior performance of our proposed model. To the best of our knowledge, our work is the pioneer which fills the gap in benchmarks and techniques for practical pedestrian trajectory prediction across different domains.

show abstract

Robust Trajectory Prediction of Multiple Interacting Pedestrians via Incremental Active Learning

Ren

Ming-Xia

et al. 2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Tra2Tra: Trajectory-to-Trajectory Prediction With a Global Social Spatial-Temporal Attentive Neural Network

Cited by 27 publications

References 36 publications

Spatial-Temporal Attentive LSTM for Vehicle-Trajectory Prediction

Spatial-Temporal Attentive LSTM for Vehicle-Trajectory Prediction

Adaptive Trajectory Prediction via Transferable GNN

Robust Trajectory Prediction of Multiple Interacting Pedestrians via Incremental Active Learning

Contact Info

Product

Resources

About