LTMSformer: A Local Trend-Aware Attention and Motion State Encoding Transformer for Multi-Agent Trajectory Prediction
This work addresses trajectory prediction for autonomous vehicles, offering an incremental improvement with specific performance gains and model efficiency.
The paper tackles the problem of modeling complex temporal-spatial dependencies for multi-agent trajectory prediction by proposing LTMSformer, which captures local temporal dependencies and high-order motion states, resulting in reduced minADE by 4.35%, minFDE by 8.74%, and MR by 20% on the Argoverse 1 dataset while achieving higher accuracy with a 68% reduction in model size compared to HiVT-128.
It has been challenging to model the complex temporal-spatial dependencies between agents for trajectory prediction. As each state of an agent is closely related to the states of adjacent time steps, capturing the local temporal dependency is beneficial for prediction, while most studies often overlook it. Besides, learning the high-order motion state attributes is expected to enhance spatial interaction modeling, but it is rarely seen in previous works. To address this, we propose a lightweight framework, LTMSformer, to extract temporal-spatial interaction features for multi-modal trajectory prediction. Specifically, we introduce a Local Trend-Aware Attention mechanism to capture the local temporal dependency by leveraging a convolutional attention mechanism with hierarchical local time boxes. Next, to model the spatial interaction dependency, we build a Motion State Encoder to incorporate high-order motion state attributes, such as acceleration, jerk, heading, etc. To further refine the trajectory prediction, we propose a Lightweight Proposal Refinement Module that leverages Multi-Layer Perceptrons for trajectory embedding and generates the refined trajectories with fewer model parameters. Experiment results on the Argoverse 1 dataset demonstrate that our method outperforms the baseline HiVT-64, reducing the minADE by approximately 4.35%, the minFDE by 8.74%, and the MR by 20%. We also achieve higher accuracy than HiVT-128 with a 68% reduction in model size.