A method and device for generating a high-precision map

Abstract

The invention discloses a method and a device for generating a high-precision map without relying on RTK (Real Time Kinematic). The method comprises the following steps: acquiring picture data from acamera; acquiring point cloud data from the laser radar; acquiring attitude information from a Global Navigation Satellite System (GNSS) / Inertia Measurement Unit (IMU); processing the picture data toextract visual feature information, and performing pose estimation according to the visual feature information extracted from the current frame, previously fused overall pose information and previously maintained map visual feature information to obtain camera pose estimation; processing the point cloud data to obtain point cloud information, and performing attitude estimation according to the point cloud information and other information to obtain radar attitude estimation; fusing the attitude information, the camera attitude estimation and the radar attitude estimation to obtain a more accurate and stable attitude estimation result; and according to a more accurate and stable attitude estimation result, fusing the picture data and the point cloud data to construct a high-precision map.

Description

technical field [0001] Generally speaking, the present invention relates to the field of automatic driving, and in particular, relates to a method and device for generating high-precision maps and positioning based on cameras, lidar and GNSS. Background technique [0002] With the development of technology, the automatic driving technology of robot-driven vehicles (for example, "UAV" or "drones, unmanned vehicles") has gradually become a hot spot. Robotic driving vehicles are being developed for a wide range of applications. A key part of autonomous driving is knowing where the vehicle is and where it is going. High-resolution maps play an important role in this. How to generate high-precision maps is the key to autonomous driving. core issues in the field. [0003] The usual high-precision map solution relies on the high-precision GPS and inertial measurement unit (IMU) integrated navigation system with RTK (Real-Time Kinematic, real-time dynamic positioning), but its cost...

AI Technical Summary

Problems solved by technology

[0003]Usual high-precision map solutions rely on high-precision GPS and inertial measurement unit (IMU) integrated navigation systems with RTK (Real-Time Kinematic, real-time dynamic positioning), But its cost is too expensive. At the same time, in the environment with weak or no signal such as high-rise buildings, tunnels, underground garages, etc., or when the vehicle turns sharply, shakes, or in bad weather, the error will become so large that it is far from being able to achieve high-precision centimeters. (cm) level requirements

Images