Multi-sensor time synchronization method and device, electronic equipment and storage medium

Abstract

The invention discloses a multi-sensor time synchronization method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining sensor data collected by at least two sensors, wherein at least two sensors comprise a first sensor and a second sensor, and the sensor data comprises a frame data value and the collection time of the frame data value; determining first acquisition time of the first sensor and a frame data value of the first sensor corresponding to the first acquisition time according to the sensor data acquired by the first sensor; according to the first acquisition time of the first sensor and the sensor data of the second sensor, determining a frame data estimation value of the second sensor corresponding to the first acquisition time; and completing time synchronization according to the frame data estimation value of the second sensor and the frame data value of the first sensor. According to the method and the device, the problem that the timestamps of the sensors with different frequencies cannot be aligned is solved, and errors caused by the time synchronization problem can be reduced by estimating the data values of the sensors at a certain moment.

Description

Technical field [0001] The present application relates to automatic driving technology, and particularly relates to a time synchronization method, apparatus, and electronic equipment, storage medium, a multi-sensor. Background technique [0002] Now, with the rapid development of the field of automated driving technologies, a single sensor can no longer meet the requirements of intelligent driving, more and more autonomous vehicles required sensors, including GPS (Global Positioning System, Global Positioning System), Lidar (Laser the radar, laser radar), IMU (inertial measurement unit, an inertial measurement unit), Odom (odometry, odometer) and a camera or the like, but the frequency of these sensors are often not the same, which leads to data received from various sensors there is no way to achieve time synchronization. [0003] For the prior art time synchronization scheme mainly based on pulse signals and the hardware manner, however, in this embodiment more sensor condition...

AI Technical Summary

Problems solved by technology

[0002] At present, with the rapid development of technology in the field of autonomous driving, a single sensor can no longer meet the requirements of intelligent driving, and more and more sensors are required for autonomous vehicles, including GPS (Global Positioning System, Global Positioning System), Lidar (Laser Radar, lidar), IMU (Inertial Measurement Unit, inertial measurement unit), Odom (Odometry, odometer) and cameras, etc., and the frequencies of these sensors are often different, which leads to the data received from each sensor no way to achieve time synchronization

[0003] The implementation schemes for time synchronization in the prior art are mainly based on hardware and pulse signals. However, in the case of more and more subsequent sensors, the real-time and accuracy of this scheme are difficult to guarantee.

Images