Virtual-real combined real-time laser radar data generation method and system and equipment

Abstract

The invention discloses a virtual-real combined real-time laser radar data generation method and system and equipment. The method comprises the following steps: rendering a simulation scene based on a high-precision OSM semantic map and generating an SUMO road network consistent with a real scene; generating a complex traffic flow scene based on the SUMO road network; synchronizing the autonomous vehicle state information to the SUMO road network, and establishing a traffic flow test scene; acquiring surrounding scene point cloud and traffic flow vehicle information according to the autonomous vehicle positioning information, and generating virtual-real combined laser radar data in real time; real-time fusion of virtual traffic flow and laser radar data of a real road scene is realized, scene information in the laser radar data comes from a real large-scale point cloud map, and vehicle point cloud is generated by a three-dimensional model of a fairly real vehicle. The generated laser radar data is used as a sensing result for automatic driving vehicle testing, so that the testability of the scene is ensured, and the complex traffic flow testing scene can be provided.

Description

technical field [0001] The invention belongs to the technical field of automatic driving vehicle testing, and in particular relates to a method, system and equipment for generating real-time laser radar data combining virtual reality. Background technique [0002] As a commonly used sensor in autonomous driving, lidar can obtain three-dimensional information of the scene and plays a vital role in unmanned driving. The point cloud data obtained by lidar is often used for space and obstacle detection, and related perception algorithms can be tested based on the data set. However, in the unmanned driving test of the vehicle in the loop, only using the lidar data of the real scene cannot test some such as For dangerous scenes such as ghost probes and emergency braking, the commonly used method of rendering virtual scenes in game engines and simulating lidar data is expensive and different from real scenes. Contents of the invention [0003] In order to provide safe and effect...

AI Technical Summary

Problems solved by technology

The point cloud data obtained by lidar is often used for space and obstacle detection, and related perception algorithms can be tested based on the data set. However, in the unmanned driving test of the vehicle in the loop, only using the lidar data of the real scene cannot test some such as Dangerous scenes such as ghost probes and emergency braking are commonly used to render virtual scenes in game engines, and the method of simulating lidar data is expensive and different from real scenes

Images