The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

Liang, Junwei; Jiang, Lu; Murphy, Kevin; Yu, Tong; Hauptmann, Alexander G.

doi:10.1109/cvpr42600.2020.01052

Cited by 156 publications

(116 citation statements)

References 37 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…However, pedestrian future behaviors are multimodal in nature, i.e., they can take multiple possible paths and their trajectories vary based on the actions taken. Several recent studies thus focused on multimodal predictions [3], [4], [34]- [39]. A common approach is using conditional variational auto-encoders (CVAEs) [35]- [37], [40].…”

Section: Background and Related Workmentioning

confidence: 99%

“…The MHP model efficiently predicted multimodal trajectories for a long term. Unlike existing studies [4], [39], the multimodality was not arbitrarily conditioned on a latent variable, but instead was conditioned on the decision-making process of the pedestrian, which is grounded in actual pedestrian behavior and thereby easier to comprehend. It can be observed that EGT metric was high initially and then decreased with increase in the prediction horizon.…”

Section: Trajectory Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal Hybrid Pedestrian: A Hybrid Automaton Model of Urban Pedestrian Behavior for Automated Driving Applications

et al. 2021

View full text Add to dashboard Cite

For automated vehicles (AVs) to navigate safely, they must be able to anticipate and predict the behavior of pedestrians. This is particularly critical in urban driving environments where risks of collisions are high. However, a major challenge is that pedestrian behavior is inherently multimodal in nature, i.e., pedestrians can plausibly take multiple paths. This is because, in large part, pedestrian behaviors are driven by unique intentions and decisions made by each pedestrian walking along a particular sidewalk or crosswalk. As described in this paper, we developed a hybrid automaton model of multimodal pedestrian behavior called Multimodal Hybrid Pedestrian (MHP). We account for multimodal pedestrian behavior by identifying pedestrian decision-making points and developing decision-making models to predict pedestrian behaviors in a probabilistic hybrid automaton framework. The resulting MHP model is more likely to predict the ground truth trajectory compared to two baseline models-a baseline hybrid automaton model and a constant velocity model. The MHP model is applicable to a wide variety of urban scenarios-midblocks, intersections, one-way, and two-way streets, etc., and the probabilistic predictions from the model can be utilized for AV motion planning. INDEX TERMS pedestrian trajectory prediction; pedestrian behavior recognition; human-centered robotics; advanced driver assistance systems (ADAS); autonomous vehicle navigation.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Section: Trajectory Predictionmentioning

confidence: 99%

Multimodal Hybrid Pedestrian: A Hybrid Automaton Model of Urban Pedestrian Behavior for Automated Driving Applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[8][9] [10] This kind of research focuses on how to use the existing historical data to choose the future direction. Liang et al [11] propose a probabilistic model (Multiverse) to calculate the future trajectory of pedestrians based on historical locations and scenes. Firstly, the Multiverse displays the position on a multi-scale grid to obtain a multi-modal representation of the future position.…”

Section: Related Workmentioning

confidence: 99%

DeepPTP: A Deep Pedestrian Trajectory Prediction Model for Traffic Intersection

Lv¹,

Li²,

Dong³

et al. 2021

KSII TIIS

View full text Add to dashboard Cite

Compared with vehicle trajectories, pedestrian trajectories have stronger degrees of freedom and complexity, which poses a higher challenge to trajectory prediction tasks. This paper designs a mode to divide the trajectory of pedestrians at a traffic intersection, which converts the trajectory regression problem into a trajectory classification problem. This paper builds a deep model for pedestrian trajectory prediction at intersections for the task of pedestrian shortterm trajectory prediction. The model calculates the spatial correlation and temporal dependence of the trajectory. More importantly, it captures the interactive features among pedestrians through the Attention mechanism. In order to improve the training speed, the model is composed of pure convolutional networks. This design overcomes the single-step calculation mode of the traditional recurrent neural network. The experiment uses Vulnerable Road Users trajectory dataset for related modeling and evaluation work. Compared with the existing models of pedestrian trajectory prediction, the model proposed in this paper has advantages in terms of evaluation indicators, training speed and the number of model parameters.

show abstract

“…GCN is widely used in action recognition [ 22 ], scene graph generation [ 23 ], video recognition [ 24 ], and other fields. Liang et al [ 25 ] designed RNN on spatial graph to encode inductive deviation of pedestrian motion patterns. A directed social graph is dynamically constructed by Zhang et al [ 26 ] to effectively obtain interactions of pedestrians.…”

Section: Related Workmentioning

confidence: 99%

EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction

Kong

Liu

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To improve foresight and make correct judgment in advance, pedestrian trajectory prediction has a wide range of application values in autonomous driving, robot interaction, and safety monitoring. However, most of the existing methods only focus on the interaction of local pedestrians according to distance, ignoring the influence of far pedestrians; the range of network input (receptive field) is small. In this paper, an extended graph attention network (EGAT) is proposed to increase receptive field, which focuses not only on local pedestrians, but also on those who are far away, to further strengthen pedestrian interaction. In the temporal domain, TSG-LSTM (TS-LSTM and TG-LSTM) and P-LSTM are proposed based on LSTM to enhance information transmission by residual connection. Compared with state-of-the-art methods, the model EGAT achieves excellent performance on both ETH and UCY public datasets and generates more reliable trajectories.

show abstract

The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

Cited by 156 publications

References 37 publications

Multimodal Hybrid Pedestrian: A Hybrid Automaton Model of Urban Pedestrian Behavior for Automated Driving Applications

Multimodal Hybrid Pedestrian: A Hybrid Automaton Model of Urban Pedestrian Behavior for Automated Driving Applications

DeepPTP: A Deep Pedestrian Trajectory Prediction Model for Traffic Intersection

EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction

Contact Info

Product

Resources

About