SLAM（Simultaneous localization and mapping）

The development of warehousing Vehicle (AGV) in 2019 is focused on from "shelf to human" to "container to human". Affected by the epidemic in China in 2020, it prompts enterprises to develop new application fields such as medical logistics AGV. However, how to change and upgrade the AGV industry cannot be separated from the small but fine subject of "obstacle avoidance".

AGV robot is an important symbol of autonomous navigation, magnetic stripe navigation from the very beginning, to the present laser navigation, auxiliary navigation GPS, inertial navigation has been developing, there are advantages and disadvantages of all sorts of navigation technology, at present, all kinds of navigation devices and sensors require separate installation, for data processing and debugging, alone is not a perfect integration solutions.

As SLAM technology matures, THE positioning and navigation of AGV robots become more accurate. SLAM (Simultaneous Localization and Mapping), namely Simultaneous Localization and map construction, was first proposed in the field of robotics. It means that a robot starts from an unknown location in an unknown environment, locates its position and attitude through repeated observed environmental characteristics in the process of movement, and then builds an incremental map of the surrounding environment according to its position, so as to achieve the purpose of simultaneous positioning and map construction.

Due to its important academic value and application value, SLAM has long been regarded as a key technology to realize fully autonomous mobile robots. At present, there are two mainstream SLAM technologies, one is visual SLAM, the other is Lidar SLAM based on Lidar, which usually adopts 2D or 3D Lidar. As the eye of AGV robot, lidar can obtain target distance, orientation, speed and other data, and provide basic data for navigation, collision avoidance, parking and other actions. At present, the mainstream 2D LiDAR can only scan a plane and collect data in a single place. AGV robots can only run in a relatively simple place, or use multiple 2D LiDAR integration to obtain more planar data to adapt to a more complex environment.3D LiDAR is the integration of quite a few 2D LiDAR. One instrument multi-line measurement can obtain multi-layer data, which can provide AGV robot with more comprehensive measurement data. Thus, it can be applied in navigation, obstacle avoidance and other fields.