Divide-and-conquer for lane-aware diverse trajectory prediction

Abstract

A method for driving path prediction is provided. The method concatenates past trajectory features and lane centerline features in a channel dimension at an agent's respective location in a top view map to obtain concatenated features thereat. The method obtains convolutional features derived from the top view map, the concatenated features, and a single representation of the training scene the vehicle and agent interactions. The method extracts hypercolumn descriptor vectors which include the convolutional features from the agent's respective location in the top view map. The method obtains primary and auxiliary trajectory predictions from the hypercolumn descriptor vectors. The method generates a respective score for each of the primary and auxiliary trajectory predictions. The method trains a vehicle trajectory prediction neural network using a reconstruction loss, a regularization loss objective, and an IOC loss objective responsive to the respective score for each of the primary and auxiliary trajectory predictions.