LG-LSTM: Modeling LSTM-Based Interactions for Multi-Agent Trajectory Prediction

Hanbing Sun, Runfa Chen, Tianyu Liu, Haiwen Wang, Fuchun SunICME 2022 · OpenReview

Abstract

Predicting the future trajectory of multi-agent in dynamic scenarios is a crucial part of autonomous driving. Despite fruitful progress, existing methods still suffer from immatu-rity in tackling social interaction modeling, which is essential for trajectory prediction. A key reason is that the previous works only consider the interaction of a single category of agents while ignoring the influence between different types of agents. This paper contends a novel framework LG-LSTM to model local and global social interactions between different types of agents by scenario graph and attention fusion. It is mainly composed of two functional components: 1. LSTM-based interaction architecture consists of LSTM-based en-coding function, graph-aware encoding function, attention-fusion encoding function, and LSTM-based decoding function. 2. Multi-task training, which conducts trajectory pre-diction and multi-agent classification. Extensive experiments on two public autonomous driving benchmarks verify the ef-ficacy of the proposed techniques and achieve superior per-formance against state-of-the-art approaches.
BibTeX
@inproceedings{sun2022lg,
  author = {Hanbing Sun and Runfa Chen and Tianyu Liu and Haiwen Wang and Fuchun Sun},
  title = {{LG-LSTM: Modeling LSTM-Based Interactions for Multi-Agent Trajectory Prediction}},
  booktitle = {ICME},
  year = {2022},
  url = {https://openreview.net/forum?id=htcuvcp6lZ},
}

Loading related content...

Figure