Intelligent automobile in-loop simulation test method based on mixed traffic flow model

Abstract

The invention provides an intelligent vehicle in-loop simulation test method based on a mixed traffic flow model, and the method comprises the steps: building a mixed traffic flow model through a generative adversarial network and an Actor-Critic network, solving a traffic flow vehicle driving strategy through a near-end strategy optimization algorithm, and carrying out the interaction with the environment to form a vehicle driving track; through a discrimination model, the generated track being distinguished from the actual track and the retrograde motion, and a reward signal being provided for the traffic flow environment. According to the method, the values of multiple influence factors of the mixed traffic flow model are combined by utilizing a combined test method, so that the test times are reduced, and the influence on the test during the interaction of the factors is explored; according to the traffic flow model generation method based on generative adversarial imitation learning, a vehicle can obtain a decision similar to an actual traffic flow; the combined case test generation method based on the greedy algorithm can improve the test efficiency. According to the method, a good improvement effect is obtained through empirical analysis.

Description

Technical field [0001] The invention belongs to the smart vehicle in the field of cyclonic test, and more specifically, it is involving a smart vehicle based on a hybrid traffic model in a ring simulation test method. Background technique [0002] Smart Cars is a comprehensive system integrating environmental perception, intelligent decision, vehicle control, multi-grade auxiliary driving, which concentrate on technology, modern sensing, information fusion, communication, artificial intelligence and automatic control, etc. Typical high-tech complex. [0003] The complete popularity of smart cars will not be in turn, therefore has the actual significance of the traditional manual driving vehicle and the automatic driving vehicle. It is foreseeable that unmanned, manual driving, non-motor vehicle and pedestrian coexistence of hybrid traffic flow related to future transportation systems will be larger. [0004] Unlike the safety test of traditional cars, the smart car does not only ...

AI Technical Summary

Problems solved by technology

Different project groups have different test procedures and methods. In the actual test process, the task of collaborative testing of various component groups cannot be well completed. At the same time, it is difficult to obtain comprehensive operating data when multiple sensor data are required. Therefore, it is difficult Holistic testing of smart cars

[0008] 2. Single test environment

[0009] The test scenarios in the existing smart car simulation test system are relatively single, and only the scenes required by the function are tested during the test, and the test environment is the same, which cannot completely reflect the real traffic scene, which leads to the failure of the safety of smart cars. , thus losing the meaning of testing

Images