Map-Adaptive Goal-Based Trajectory Prediction
Zhang, Lingyao, Su, Po-Hsun, Hoang, Jerrick, Haynes, Galen Clark, Marchetti-Bowick, Micol
We present a new method for multi-modal, long-term vehicle trajectory prediction. Our approach relies on using lane centerlines captured in rich maps of the environment to generate a set of proposed goal paths for each vehicle. Using these paths -- which are generated at run time and therefore dynamically adapt to the scene -- as spatial anchors, we predict a set of goal-based trajectories along with a categorical distribution over the goals. This approach allows us to directly model the goal-directed behavior of traffic actors, which unlocks the potential for more accurate long-term prediction. Our experimental results on both a large-scale internal driving dataset and on the public nuScenes dataset show that our model outperforms state-of-the-art approaches for vehicle trajectory prediction over a 6-second horizon. We also empirically demonstrate that our model is better able to generalize to road scenes from a completely new city than existing methods.
Sep-9-2020
- Country:
- North America > United States (0.46)
- Genre:
- Research Report > Promising Solution (0.34)
- Industry:
- Transportation
- Ground > Road (0.46)
- Infrastructure & Services (0.46)
- Transportation
- Technology: