An evaluation framework for predicting trajectories in traffic prediction for autonomous vehicles

摘要

According to one embodiment, when a predicted trajectory is received, a plurality of feature sets are extracted from at least some of the trajectory points of the predicted trajectory. The predicted trajectory is predicted using a prediction method or algorithm based on sensed data that senses objects in the driving environment around the autonomous vehicle (ADV). The extracted features are supplied to a predetermined DNN model to generate a similarity score. The similarity score indicates a difference or similarity between the predicted trajectory and the previous actual trajectory for DNN model training. The similarity score can be used to evaluate a prediction method that predicts a prediction trajectory. [Selection] Figure 7