MSN: Multi-Style Network for Trajectory Prediction

Trajectory prediction aims to forecast agents' possible future locations considering their observations along with the video context. It is strongly needed for many autonomous platforms like tracking, detection, robot navigation, and self-driving cars. Whether it is agents' internal personality factors, interactive behaviors with the neighborhood, or the influence of surroundings, all of them might represent impacts on agents' future plannings. However, many previous methods model and predict agents' behaviors with the same strategy or feature distribution, making them challenging to give predictions with sufficient style differences. This manuscript proposes the Multi-Style Network (MSN), which utilizes style proposal and stylized prediction two sub-networks, to give agents multi-style predictions in a novel categorical way adaptively. The proposed network contains a series of style channels, and each channel is bound to a unique and specific behavior style. In detail, we use agents' end-point plannings and their interaction context as the basis for the behavior classification, so as to adaptively learn multiple diverse behavior styles through these channels. Then, we assume that the target agents will plan their future behaviors according to each of these categorized styles, thus utilizing different style channels to give potential predictions with significant style differences in parallel. Experiments show that MSN outperforms current state-of-the-art methods up to 10\% quantitatively on two widely used datasets, and presents better multi-style characteristics qualitatively.