Map-Adaptive Goal-Based Trajectory Prediction

Abstract

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.

arXiv commentPublished at CoRL 2020

References in corpus (4)

• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• IntentNet: Learning to Predict Intention from Raw Sensor Data
• Probabilistic Multi-modal Trajectory Prediction with Lane Attention for Autonomous Vehicles
• Lane Attention: Predicting Vehicles' Moving Trajectories by Learning Their Attention over Lanes

Cited by in corpus (7)

• Stepwise Goal-Driven Networks for Trajectory Prediction
• Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans
• THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling
• Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions
• Physically Feasible Vehicle Trajectory Prediction
• Trajectory Prediction with Graph-based Dual-scale Context Fusion
• Jointly Learning Agent and Lane Information for Multimodal Trajectory Prediction