マルチヘッド注意機構によるマルチモーダル車両運動の同時予測
Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting
道路上の全車両の位置を多峰確率密度関数の系列として同時予測するマルチヘッド注意機構ベースの手法を提案し、同一データセットで最先端モデルを上回る予測尤度を達成した。
著者: Jean Mercat, Thomas Gilles, Nicole El Zoghby, Guillaume Sandou, Dominique Beauvois, Guillermo Pita Gil
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
This paper presents a novel vehicle motion forecasting method based on multi-head attention. It produces joint forecasts for all vehicles on a road scene as sequences of multi-modal probability density functions of their positions. Its architecture uses multi-head attention to account for complete interactions between all vehicles, and long short-term memory layers for encoding and forecasting. It relies solely on vehicle position tracks, does not need maneuver definitions, and does not represent the scene with a spatial grid. This allows it to be more versatile than similar model while combining any forecasting capabilities, namely joint forecast with interactions, uncertainty estimation, and multi-modality. The resulting prediction likelihood outperforms state-of-the-art models on the same dataset.
