US 11,772,681 B2
Method and apparatus for processing autonomous driving simulation data, and electronic device
Shengjian Guo, Beijing (CN); Zhisheng Hu, Beijing (CN); Zhenyu Zhong, Beijing (CN); and Kang Li, Beijing (CN)
Assigned to BAIDU.COM TIMES TECHNOLOGY (BEIJING) CO., LTD., Beijing (CN)
Filed by BAIDU.COM TIMES TECHNOLOGY (BEIJING) CO., LTD., Beijing (CN)
Filed on Aug. 31, 2021, as Appl. No. 17/463,501.
Prior Publication US 2022/0126860 A1, Apr. 28, 2022
Int. Cl. G07C 5/04 (2006.01); B60W 60/00 (2020.01); B60W 50/00 (2006.01); H04L 65/61 (2022.01)
CPC B60W 60/001 (2020.02) [B60W 50/0098 (2013.01); G07C 5/04 (2013.01); H04L 65/61 (2022.05); B60W 2050/0022 (2013.01); B60W 2556/35 (2020.02); B60W 2556/45 (2020.02)] 16 Claims
OG exemplary drawing
 
1. A method for processing autonomous driving simulation data, comprising:
determining a type of a message transmitted between a simulation system and an auto driving system (ADS);
determining a data acquisition mode based on the type of the message;
obtaining a data stream transmitted between the simulation system and the ADS based on the data acquisition mode; and
determining performance of the ADS based on the data stream,
wherein each data stream comprises a data sequence and a timestamp of each piece of data, and determining the performance of the ADS based on the data stream comprises:
determining environmental data and autonomous driving data at each timestamp by combining data sequences of a plurality of data streams based on the timestamp of each piece of data in each data stream;
obtaining reference driving data at each timestamp based on the environmental data at each timestamp;
comparing each kind of driving data in the autonomous driving data with the kind of driving data in the reference driving data at a timestamp same as the autonomous driving data to determine a matching degree of each kind of driving data at the timestamp;
performing weighted fusion on the matching degree of each kind of driving data at the timestamp based on a predetermined weight of each kind of driving data to obtain the matching degree between the autonomous driving data and the reference driving data at the timestamp; and
determining the performance of the ADS based on the matching degree between the autonomous driving data and the reference driving data at each timestamp.