arXiv:2106.11467
Multimodal trajectory forecasting based on discrete heat map
원문 초록
In Argoverse motion forecasting competition, the task is to predict the probabilistic future trajectory distribution for the interested targets in the traffic scene. We use vectorized lane map and 2 s targets' history trajectories as input. Then the model outputs 6 forecasted trajectories with probability for each target.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TrajFlow: A Generative Framework for Occupancy Density Estimation Using Normalizing Flows
Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting
Streaming Motion Forecasting for Autonomous Driving
Staged Contact-Aware Global Human Motion Forecasting
trajdata: A Unified Interface to Multiple Human Trajectory Datasets
Trajectory Forecasting on Temporal Graphs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.