Automatic driving test scene construction method, device and equipment and readable storage medium

Abstract

The invention discloses an automatic driving test scene construction method, device and equipment and a readable storage medium, and the method comprises the steps: carrying out the extraction of a primitive scene from a real traffic scene, building a primitive scene description model, and selecting a description variable value from a primitive scene description variable distribution interval; carrying out random sampling on the description variables according to description variable distribution by a Monte Carlo method based on importance sampling to generate a test element scene; generatinga test scene according to the parameter test primitive scene of the test scene element in the test task and a recombination method. According to the method, an actual complex system can be directly simulated, the problem of result distortion caused by complex system simplification is effectively solved, and the problem of dimensionality disasters that high-dimensional problem numerical solution errors are rapidly increased along with increase of dimensionality is avoided; a high-risk scene enhanced generation method is adopted, more high-risk scenes are generated with lower calculation overhead, the number of the high-risk scenes in the generated scenes is effectively increased, the number of the low-risk scenes is reduced, and the test efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of automatic driving test, and relates to a method, a device, a device and a readable storage medium for constructing an automatic driving test scene. Background technique [0002] Self-driving cars are intelligent vehicles that integrate environmental perception, decision-making planning, and control execution, and represent the strategic commanding heights of future automotive technology. With the development of a series of key technologies, self-driving cars provide new ways to solve problems such as "traffic accidents, traffic congestion, environmental pollution, and energy shortages." A scientific and complete test verification and evaluation system is crucial to improving the efficiency of research and development of autonomous vehicles, improving relevant laws and regulations, and promoting the development of intelligent transportation. [0003] In addition, unlike the human-vehicle binary independen...

AI Technical Summary

Problems solved by technology

However, there is currently a lack of a method for generating autonomous driving test scenarios, which cannot effectively simulate real traffic scenarios

Images