Class-Aware Attention for Multimodal Trajectory Prediction
This addresses the problem of accurate and efficient trajectory prediction for autonomous vehicles, though it is incremental by focusing on physical property integration.
The paper tackles multimodal trajectory prediction in autonomous driving by incorporating physical properties like object class and dimensions via a weighted attention module, achieving state-of-the-art results on the nuScenes benchmark with real-time performance over 300 FPS.
Predicting the possible future trajectories of the surrounding dynamic agents is an essential requirement in autonomous driving. These trajectories mainly depend on the surrounding static environment, as well as the past movements of those dynamic agents. Furthermore, the multimodal nature of agent intentions makes the trajectory prediction problem more challenging. All of the existing models consider the target agent as well as the surrounding agents similarly, without considering the variation of physical properties. In this paper, we present a novel deep-learning based framework for multimodal trajectory prediction in autonomous driving, which considers the physical properties of the target and surrounding vehicles such as the object class and their physical dimensions through a weighted attention module, that improves the accuracy of the predictions. Our model has achieved the highest results in the nuScenes trajectory prediction benchmark, out of the models which use rasterized maps to input environment information. Furthermore, our model is able to run in real-time, achieving a high inference rate of over 300 FPS.