A system includes a memory device and a processing device operably coupled to the memory device to receive a set of input data including a roadmap, the roadmap including an autonomous vehicle driving path, modify the roadmap to obtain a modified roadmap by adjusting a trajectory of the autonomous vehicle driving path, and transmit the modified roadmap to the memory device. A set of artifacts is placed along one or more lane boundaries of the modified roadmap to generate a synthetic scene, and a machine learning model for navigating the autonomous vehicle is trained based on the synthetic scene.
一种系统,包括存储器设备和处理设备,可操作地耦合到存储器设备,以接收包括路线图的一组输入数据,所述路线图包括自主载具驾驶路径,通过调整自主载具驾驶路径的轨迹,修改路线图以获得修改的路线图,沿修改的路线图的一个或多个车道边界放置一组人工制品以生成合成场景,并基于合成场景训练用于导航自主载具的机器学习模型。
Implementing synthetic scene of autonomous vehicle
实现自主载具的合成场景
2023-01-17
Patent
Electronic Resource
Chinese
SYNTHETIC SCENE GENERATION FOR AUTONOMOUS VEHICLE TESTING
European Patent Office | 2024
|Scene-Graph Embedding for Robust Autonomous Vehicle Perception
Springer Verlag | 2023
|