Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Network

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xin, Guipeng, Chu, Duanfeng, Lu, Liping, Deng, Zejian, Lu, Yuang, Wu, Xigang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929638985433088
author Xin, Guipeng
Chu, Duanfeng
Lu, Liping
Deng, Zejian
Lu, Yuang
Wu, Xigang
author_facet Xin, Guipeng
Chu, Duanfeng
Lu, Liping
Deng, Zejian
Lu, Yuang
Wu, Xigang
contents Trajectory prediction is crucial for autonomous driving as it aims to forecast the future movements of traffic participants. Traditional methods usually perform holistic inference on the trajectories of agents, neglecting the differences in prediction difficulty among agents. This paper proposes a novel Difficulty-Guided Feature Enhancement Network (DGFNet), which leverages the prediction difficulty differences among agents for multi-agent trajectory prediction. Firstly, we employ spatio-temporal feature encoding and interaction to capture rich spatio-temporal features. Secondly, a difficulty-guided decoder controls the flow of future trajectories into subsequent modules, obtaining reliable future trajectories. Then, feature interaction and fusion are performed through the future feature interaction module. Finally, the fused agent features are fed into the final predictor to generate the predicted trajectory distributions for multiple participants. Experimental results demonstrate that our DGFNet achieves state-of-the-art performance on the Argoverse 1\&2 motion forecasting benchmarks. Ablation studies further validate the effectiveness of each module. Moreover, compared with SOTA methods, our method balances trajectory prediction accuracy and real-time inference speed.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18551
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Network
Xin, Guipeng
Chu, Duanfeng
Lu, Liping
Deng, Zejian
Lu, Yuang
Wu, Xigang
Robotics
Artificial Intelligence
Trajectory prediction is crucial for autonomous driving as it aims to forecast the future movements of traffic participants. Traditional methods usually perform holistic inference on the trajectories of agents, neglecting the differences in prediction difficulty among agents. This paper proposes a novel Difficulty-Guided Feature Enhancement Network (DGFNet), which leverages the prediction difficulty differences among agents for multi-agent trajectory prediction. Firstly, we employ spatio-temporal feature encoding and interaction to capture rich spatio-temporal features. Secondly, a difficulty-guided decoder controls the flow of future trajectories into subsequent modules, obtaining reliable future trajectories. Then, feature interaction and fusion are performed through the future feature interaction module. Finally, the fused agent features are fed into the final predictor to generate the predicted trajectory distributions for multiple participants. Experimental results demonstrate that our DGFNet achieves state-of-the-art performance on the Argoverse 1\&2 motion forecasting benchmarks. Ablation studies further validate the effectiveness of each module. Moreover, compared with SOTA methods, our method balances trajectory prediction accuracy and real-time inference speed.
title Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Network
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2407.18551