SCANeR-based automatic driving simulation test model construction method

Abstract

The invention provides an SCANeR-based automatic driving simulation test model construction method, which comprises the following steps of S1, deconstructing and reconstructing scene data, and extracting scene feature elements; S2, carrying out static scene editing according to the scene feature elements; S3, performing dynamic scene editing according to the scene feature elements; S4, interactingthe content in the step S2 and the content in the step S3 in SCANeR, and constructing a virtual driving test scene; and S5, determining whether a test condition is met or not, and if not, returning to the step S2; if so, starting testing. According to the SCANeR-based automatic driving simulation test model construction method of the invention, in combination with cloud computing, high-precisionmaps, virtual reality and other technologies, driving scene virtual simulation can extend tests to more application scenes, and therefore, the SCANeR-based automatic driving simulation test model construction method has a great acceleration propulsion effect on the research and development of automatic driving functions of L2 and above.

Description

technical field [0001] The invention belongs to the technical field of intelligent driving, and in particular relates to a method for constructing a SCANeR-based automatic driving simulation test model. Background technique [0002] At present, the research on intelligent networked vehicles at home and abroad is in an explosive period. Many new technologies and methods are driving the industry to advance rapidly. The research on autonomous driving has also shifted from L2 to L3\L4 or even L5. Since intelligent networked vehicles basically no longer rely on humans for driving from the L3 level, safety has become an important consideration for the development of the industry. In the process of autonomous driving technology research, virtual simulation scene data is the basic data resource for the R&D and testing of intelligent connected vehicles, an important "case library" and "exercise set" for evaluating the functional safety of intelligent connected vehicles, and an import...

AI Technical Summary

Problems solved by technology

However, there are currently many simulation test software for autonomous driving technology. In the process of scene construction, there are various scene formats, poor scene rendering results, distortion of road information, and mismatching of scene interface communication, etc., which seriously affect the accuracy of automatic driving simulation test. and security

Images