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

TL;DR

This paper introduces DGFNet, a novel multi-agent trajectory prediction model that uses difficulty-guided feature enhancement to improve accuracy and efficiency in autonomous driving scenarios.

Contribution

The paper proposes a difficulty-guided decoding approach and feature interaction modules, achieving state-of-the-art results on benchmark datasets.

Findings

Achieves state-of-the-art performance on Argoverse benchmarks.

Balances trajectory accuracy with real-time inference speed.

Validates effectiveness through ablation studies.

Abstract

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.