SLAM system based on data association and error detection and method for constructing data association

Abstract

The invention provides an SLAM system based on data association and error detection and a method for constructing data association, wherein the system comprises a frontend module and a key frame database. The process for constructing data association by the frontend module comprises the steps of S100, receiving a common frame and a predicated pose Tpredict of the common frame; S200, searching n candidate frames which are similar with the common frame from a key frame database, and classifying the n candidate frames to a global candidate frame set and a local candidate frame set; S300, calculating a pose transform relation Tpc between each candidate frame and the common frame, and using Tpc as an association result; S400, performing error testing on the association result according to classification of the candidate frame for filtering error association results; S500, determining whether a correct association result is generated after S400, and if yes, returning for executing the S100,and otherwise, executing S600; and S600, creating a new key frame according to the historical common frame in a temporary region, the predicated pose, the common frame and the predicated pose thereof.

Description

technical field [0001] The invention belongs to the field of mobile robots, and in particular relates to a SLAM system based on data association and error detection and a method for constructing data association. Background technique [0002] The application of mobile robots is becoming more and more common. For example, mobile robots can be used in mobile patrol stations. Such mobile patrol stations are equipped with appropriate sensors, enabling them to drive autonomously in the environment while monitoring abnormal conditions in the environment, such as monitoring whether there is illegal intrusion or whether there are pedestrians falling and so on. [0003] For such mobile robots, there is usually a requirement for autonomous movement, and the autonomous movement of robots generally relies on simultaneous localization and mapping (SLAM) technology. The current mainstream SLAM technology mainly uses lidar or camera as the associated data source. The disadvantage of the...

AI Technical Summary

Problems solved by technology

The disadvantage of the lidar solution is that the sensor is relatively expensive, and the global closed-loop ability is relatively poor. At the same time, it does not help the robot to understand the semantics of the environment. It is not suitable for general application to consumer robots.

Correspondingly, vision-based SLAM schemes have been widely used in the field of mobile robots, while the current mainstream visual SLAM schemes have high requirements for computing power, rely on high frame rate and high real-time operation, and have specific requirements for usage scenarios. There are also certain requirements. Robust results cannot be obtained in low-texture or repeated-texture areas, and it is easy to lose track. After visual tracking fails, a complex relocation mechanism is required, and the robot needs to actively cooperate to move to the previous area. , this is difficult to achieve for most robot systems without human intervention, and it is also a relatively clumsy behavior. Therefore, the current mainstream visual SLAM solutions are difficult to implement on ordinary embedded hardware platforms.

Images