An Adversarial Learned Trajectory Predictor with Knowledge-Rich Latent Variables

He, Caizhen; Yang, Biao; Chen, Lanping; Yan, Guocheng

doi:10.1007/978-3-030-60636-7_4

Cited by 2 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…obs (10) Afterward, the sparse self-attention module calculates the first U dot product pairs with high correlation, and then multiplier them with V enc to get the attention matrix A enc as follows:…”

Section: Pipeline Of the Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting Future Trajectories with an Improved Transformer Network

Wu¹,

Zhang²,

Wang³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

An increase in car ownership brings convenience to people's life. However, it also leads to frequent traffic accidents. Precisely forecasting surrounding agents' future trajectories could effectively decrease vehicle-vehicle and vehicle-pedestrian collisions. Long-short-term memory (LSTM) network is often used for vehicle trajectory prediction, but it has some shortages such as gradient explosion and low efficiency. A trajectory prediction method based on an improved Transformer network is proposed to forecast agents' future trajectories in a complex traffic environment. It realizes the transformation from sequential step processing of LSTM to parallel processing of Transformer based on attention mechanism. To perform trajectory prediction more efficiently, a probabilistic sparse self-attention mechanism is introduced to reduce attention complexity by reducing the number of queried values in the attention mechanism. Activate or not (ACON) activation function is adopted to select whether to activate or not, hence improving model flexibility. The proposed method is evaluated on the publicly available benchmarks nextgeneration simulation (NGSIM) and ETH/UCY. The experimental results indicate that the proposed method can accurately and efficiently predict agents' trajectories.

show abstract

Section: Pipeline Of the Proposed Methodsmentioning

confidence: 99%

“…With the developments of machine learning [3][4][5], researchers proposed two kinds of prediction methods, including model-driven [6,7] and data-driven [8][9][10]. For the former, some researchers used the Markov chain and Kalman filter [6,7] to perform trajectory prediction.…”

Section: Figure 1: Driving Scenario Of An Autonomous Vehiclementioning

confidence: 99%

Forecasting Future Trajectories with an Improved Transformer Network

Wu¹,

Zhang²,

Wang³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Yang et al [35] and Cai et al [2] modeled pedestrians' motion histories and predicted their future trajectories in urban traffic scenes. He et al [36] proposed a multi-input latent variable predictor to increase the prediction accuracy with the scenes' hidden information.…”

Section: Introductionmentioning

confidence: 99%

“…He et al. [36] proposed a multi‐input latent variable predictor to increase the prediction accuracy with the scenes' hidden information.…”

Section: Introductionmentioning

confidence: 99%

IRLSOT: Inverse reinforcement learning for scene‐oriented trajectory prediction

Chen

Xu³

et al. 2022

IET Intelligent Trans Sys

Self Cite

View full text Add to dashboard Cite

Forecasting pedestrians' future trajectory in unknown complex environments is essential to autonomous navigation in real‐world applications, for example, for self‐driving cars and collision warnings. However, modern observed trajectory‐based prediction methods may easily over‐fit to complex or rare scenes because they do not entirely understand the correlations between scenes and trajectories. To address the over‐fitting problem, an Inverse Reinforcement Learning for Scene‐oriented Trajectory Prediction (IRLSOT) is proposed in this work. The authors' method can be divided into three modules. First, the inverse reinforcement learning module generates the optimal policy by extracting features from scenes and pedestrians' observed trajectories. A lightweight ENet is used to extract features from scenes. Afterwards, the path sampling module introduces a Gumbel Softmax Trick (GST) to improve the accuracy of optimal policy sampling. Different paths are generated on the basis of the optimal policies. Finally, the information fusion module uses the proposed Scene Based Attention (SBA) to fuse the path and trajectory information, then outputs the predicted trajectories. Comparison results show that IRLSOT improves performance on Stanford Drone Database(SDD) by 5.9%$\%$. Furthermore, the authors' test IRLSOT on multi‐agent scenarios and the authors' own data sets, and results demonstrate that IRLSOT can enhance the generalization of trajectory prediction to rare or new scenes.

show abstract

An Adversarial Learned Trajectory Predictor with Knowledge-Rich Latent Variables

Cited by 2 publications

References 17 publications

Forecasting Future Trajectories with an Improved Transformer Network

Forecasting Future Trajectories with an Improved Transformer Network

IRLSOT: Inverse reinforcement learning for scene‐oriented trajectory prediction

Contact Info

Product

Resources

About