Methods, equipment, and vehicles for autonomous vehicle behavior decision-making and model building

Abstract

This disclosure provides a method, device, and vehicle for autonomous vehicle behavior decision-making and model building, relating to the field of artificial intelligence technology, specifically autonomous driving, decision planning, and other technical fields. The autonomous vehicle behavior decision-making method includes: acquiring a pre-built behavior decision model, the behavior decision model including: a network structure and network parameters, the network structure including network nodes, the network nodes including behavior nodes and candidate state variable nodes; based on the network structure, determining a target state variable node for the behavior node from the candidate state variable nodes, and acquiring the current observation value of the target state variable node; based on the network parameters, acquiring the conditional probability of a candidate behavior under the current observation value; and based on the conditional probability, determining a target behavior from the candidate behaviors. This disclosure can improve the accuracy and efficiency of driving behavior decision-making.

Images