Abstract: A neural network, and an autonomous driving method and apparatus are provided. The neural network includes a mixture of experts MOE network and N parallel head networks. The MOE network is used to perform feature extraction and feature fusion on input data to obtain N types of feature data, where the input data includes ego vehicle data, obstacle data, road topology data, and navigation data, the N types of feature data are in a one-to-one correspondence with the N parallel head networks, and each of the N parallel head networks corresponds to one autonomous driving task; and each head network performs one corresponding autonomous driving task based on one type of feature data that is correspondingly input, where the autonomous driving task includes a prediction task, a decision task, and a planning task. Each autonomous driving task can maintain independence to some extent while maintaining certain interaction.

Abstract: This application provides example driving behavior determining methods and example related devices thereof. One example method in this application includes obtaining first driving data of a first vehicle and second driving data of a second vehicle. A driving behavior set in which the first vehicle has no risk of collision with the second vehicle is obtained based on the first driving data and the second driving data. The first driving data and the second driving data are processed by using a target model to obtain a predicted driving behavior of the first vehicle. In response to detecting that the driving behavior set includes the predicted driving behavior, the predicted driving behavior is determined as a driving behavior to be performed by the first vehicle.