STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction

By Yingfan Huang, Huikun Bi, Zhaoxin Li, Tianlu Mao, Zhaoqi Wang. IEEE International Conference on Computer Vision, 2019

643 citations recorded by the source corpus.

Human trajectory prediction is challenging and critical in various applications (e.g., autonomous vehicles and social robots). Because of the continuity and foresight of the pedestrian movements, the moving pedestrians in crowded spaces will consider both spatial and temporal interactions to avoid future collisions. However, most of the existing methods ignore the temporal correlations of interactions with other pedestrians involved in a scene. In this work, we propose a Spatial-Temporal Graph Attention network (STGAT), based on a sequence-to-sequence architecture to predict future trajectories of pedestrians. Besides the spatial interactions captured by the graph attention mechanism at each time-step, we adopt an extra LSTM to encode the temporal correlations of interactions. Through comparisons with state-of-the-art methods, our model achieves superior performance on two publicly available crowd datasets (ETH and UCY) and produces more "socially" plausible trajectories for pedestrians.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f2bd59f9ca31e941f63b900510109308d8ec9acf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Survey on Trajectory-Prediction Methods for Autonomous Driving (2022, neutral): “[143] apply GAT to the trajectory prediction.”
TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving (2022, background): “Attention has been explored in the context of driving for lane changing [65], object detection [31], [66], [67], [68], motion forecasting [31], [69], [70], [71], [72], [73], [74], [75], [76], [77], driver attention prediction [78], [79] and recently also for end-to-end driving [39], [41].”
Human motion trajectory prediction: a survey (2019, background): “);Huynh and Alaghband (2019);Nikhil and Tran Morris(2018);Xu et al.(2018);Fernando et al.(2018);Cui et al.(2019);Luo and Cai(2019);Hong et al.(2019);Pei et al.(2019);Altch´e and de La Fortelle (2017);Huang et al. (2019);Chai et al.(2019);Amirian et al.(2019);Blaiotta(2019);Dai et al.(2019);Kosaraju ”
AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting (2021, methodology): “Alternatively, meth-ods like [45, 18] ﬁrst use social models to produce social features for each agent at each independent timestep and then apply temporal models over the social features.”
Multi-Modal Fusion Transformer for End-to-End Autonomous Driving (2021, background): “Attention for Autonomous Driving: Attention has been explored in the context of driving for lane changing [13], object detection [11, 32] and motion forecasting [32, 50, 49, 28, 15, 30, 29, 56].”
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion (2022, methodology): “In addition, the spatialtemporal graph model is applied to jointly model the temporal clues and social interactions [15, 16, 30, 38, 44, 50].”
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting (2022, methodology): “• Constant Velocity Model (CVM) [36]: a simple but effective baseline that estimates future positions by considering solely the latest two timesteps; • ST-GAT [20]: graph-based attention network using LSTMs to model temporal correlations.”
HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction (2022, background): “Since social interactions are ubiquitous in traffic scenarios and significantly impact the future motions of traffic agents, many motion prediction approaches have considered the dependencies between agents’ behaviors and reasoned agent-agent interactions using social pooling [2,13,23], graph neural”
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction (2020, methodology): “, social pooling [1, 16], attention mechanism [48, 45, 22] and graph neural networks [21, 53], are used to improve the trajectory prediction with social interaction modeling.”
Wayformer: Motion Forecasting via Simple & Efficient Attention Networks (2022, methodology): “The order of applying attention over {temporal, social/spatial} dimensions has been studied with two different common patterns: (a) Temporal first [31, 35, 45] (b) Social/Spatial first [46, 47].”