Trajectory Forecasting on Temporal Graphs
This addresses the challenge of accurate trajectory forecasting in highly dynamic traffic scenes for self-driving applications, representing an incremental improvement over existing methods.
The paper tackles the problem of predicting future locations of agents in self-driving by proposing a temporal graph representation to capture dynamic scene changes, achieving state-of-the-art performance on the Argoverse benchmark.
Predicting future locations of agents in the scene is an important problem in self-driving. In recent years, there has been a significant progress in representing the scene and the agents in it. The interactions of agents with the scene and with each other are typically modeled with a Graph Neural Network. However, the graph structure is mostly static and fails to represent the temporal changes in highly dynamic scenes. In this work, we propose a temporal graph representation to better capture the dynamics in traffic scenes. We complement our representation with two types of memory modules; one focusing on the agent of interest and the other on the entire scene. This allows us to learn temporally-aware representations that can achieve good results even with simple regression of multiple futures. When combined with goal-conditioned prediction, we show better results that can reach the state-of-the-art performance on the Argoverse benchmark.