GAMDTP: グラフアテンションMambaネットワークによる動的軌道予測
GAMDTP: Dynamic Trajectory Prediction with Graph Attention Mamba Network
自動運転のための軌道予測手法GAMDTPを提案。グラフ畳み込み層で自己アテンションとMamba-SSMをゲート機構で融合し、HDマップと履歴軌道から高精度に予測する。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yunxiang Liu, Hongkuo Niu, Jianlin Zhu
分類: cs.AI, cs.RO
原文アブストラクト
Accurate motion prediction of traffic agents is crucial for the safety and stability of autonomous driving systems. In this paper, we introduce GAMDTP, a novel graph attention-based network tailored for dynamic trajectory prediction. Specifically, we fuse the result of self attention and mamba-ssm through a gate mechanism, leveraging the strengths of both to extract features more efficiently and accurately, in each graph convolution layer. GAMDTP encodes the high-definition map(HD map) data and the agents' historical trajectory coordinates and decodes the network's output to generate the final prediction results. Additionally, recent approaches predominantly focus on dynamically fusing historical forecast results and rely on two-stage frameworks including proposal and refinement. To further enhance the performance of the two-stage frameworks we also design a scoring mechanism to evaluate the prediction quality during the proposal and refinement processes. Experiments on the Argoverse dataset demonstrates that GAMDTP achieves state-of-the-art performance, achieving superior accuracy in dynamic trajectory prediction.
