Training, testing and validating autonomous machines using simulated environments

• Main Authors: ZEDLEWSKI JOHN, BEESON CURTIS, HEINRICH GREG, TAYLOR ZACHARY, LEBAREDIAN REV, COX MICHAEL, DALY MARK, DELAUNEY CLAIRE, CAMPBELL MATTHEW, AULD DAVID, FARABET CLEMENT, TAMASI TONY, HICOK GARY
• Format: Patent
• Language: Chinese; English
• Published: 10.11.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONTROLLING; COUNTING; LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS; MOTOR VEHICLES; PERFORMING OPERATIONS; PHYSICS; REGULATING; SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES; TRAILERS; TRANSPORTING

In various examples, physical sensor data may be generated by a vehicle in a real-world environment. The physical sensor data may be used to train deep neural networks (DNNs). The DNNs may then be tested in a simulated environment - in some examples using hardware configured for installation in a vehicle to execute an autonomous driving software stack - to control a virtual vehicle in the simulated environment or to otherwise test, verify, or validate the outputs of the DNNs. Prior to use by the DNNs, virtual sensor data generated by virtual sensors within the simulated environment may be encoded to a format consistent with the format of the physical sensor data generated by the vehicle. 在各种示例中，物理传感器数据可以由车辆在现实环境中生成。物理传感器数据可用于训练深度神经网络(DNN)。然后可以在模拟环境中对DNN进行测试-在某些示例中，使用配置为安装在车辆中以执行自动驾驶软件栈的硬件-在模拟环境中控制虚拟车辆或以其他方式测试，验证或确认DNN的输出。在由DNN使用之前，可以将由模拟环境内的虚拟传感器生成的虚拟传感器数据编码为与由车辆生成的物理传感器数据的格式一致的格式。