Long-term Prediction of Vehicle Behavior using Short-term Uncertainty-aware Trajectories and High-definition Maps
This addresses the critical safety need for accurate motion prediction in autonomous vehicles, though it is incremental as it unifies existing approaches.
The paper tackles the problem of predicting vehicle motion for self-driving cars by combining learned short-term uncertainty-aware trajectories with lane-based paths, resulting in improved accuracy at both short- and long-term horizons and outperforming state-of-the-art methods in real-world experiments.
Motion prediction of surrounding vehicles is one of the most important tasks handled by a self-driving vehicle, and represents a critical step in the autonomous system necessary to ensure safety for all the involved traffic actors. Recently a number of researchers from both academic and industrial communities have focused on this important problem, proposing ideas ranging from engineered, rule-based methods to learned approaches, shown to perform well at different prediction horizons. In particular, while for longer-term trajectories the engineered methods outperform the competing approaches, the learned methods have proven to be the best choice at short-term horizons. In this work we describe how to overcome the discrepancy between these two research directions, and propose a method that combines the disparate approaches under a single unifying framework. The resulting algorithm fuses learned, uncertainty-aware trajectories with lane-based paths in a principled manner, resulting in improved prediction accuracy at both shorter- and longer-term horizons. Experiments on real-world, large-scale data strongly suggest benefits of the proposed unified method, which outperformed the existing state-of-the-art. Moreover, following offline evaluation the proposed method was successfully tested onboard a self-driving vehicle.