Unmanned vehicle simulation test case generation method and system

Abstract

The invention discloses an unmanned vehicle simulation test case generation method and system, and relates to the technical field of unmanned vehicle testing. The method comprises the steps: selectinga test site of a test case in a simulation environment; determining initial states of a main vehicle and a participant in the test case, and generating the main vehicle and the participants in the test site; designing an action behavior of the participant in the test case according to an atomic behavior action, and designing a judgment rule of the main vehicle; connecting a tested object to the main vehicle of the simulation environment, and controlling the participant to carry out testing; and analyzing test data according to the action behavior of the participant and the judgment rule of the main vehicle, and returning a test result. The limitation that a traditional unmanned vehicle simulation test uses a fixed test case is broken through, great flexibility is brought to the design ofthe test case, and a technical foundation is laid for model-based test verification in the field of automatic driving.

Description

technical field [0001] The invention relates to the technical field of unmanned vehicle testing, in particular to a method and system for generating unmanned vehicle simulation test cases. Background technique [0002] With the continuous advancement of artificial intelligence technology, unmanned vehicle technology has received extensive attention from the scientific and industrial circles. Some well-known companies including Tesla, Waymo, Uber, and Baidu have applied advanced technologies such as convolutional neural networks, recurrent neural networks, deep reinforcement learning, and model predictive control to unmanned vehicle products. Unfortunately, fatal accidents with Tesla and Uber have shown that current self-driving car technology is still not safe. According to the RAND report, in the real world, it is not feasible to evaluate the safety and reliability of unmanned vehicles due to the huge time cost and public safety. Therefore, it is necessary to use a virtua...

AI Technical Summary

Problems solved by technology

However, compared with the huge data space of real driving situations, the use of these fixed test cases for unmanned vehicle simulation testing is obviously unable to fully prove the safety and reliability of unmanned vehicles

This greatly limits the practical application significance in the field of unmanned vehicle simulation testing, and hinders the rapid development and progress of technology in the field of unmanned vehicle simulation testing.

Images