CVJun 22, 2021
Multimodal trajectory forecasting based on discrete heat map
arXiv:2106.11467v1
Originality Synthesis-oriented
AI Analysis
This work addresses motion forecasting for autonomous vehicles, but appears incremental as it applies an existing method to a specific competition dataset.
The paper tackles the problem of predicting future trajectory distributions for targets in traffic scenes, using vectorized lane maps and history trajectories as input to output six forecasted trajectories with probabilities.
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.