I have recently read two very good articles on SLAM technology, which is very helpful for understanding the history of SLAM technology, current research status and future prospects. Reprinted here! (click on the blue font)

 

 Talking about SLAM technology (on)

 Talking about SLAM technology (below)

 

With the popularity of robots, drones, driverless, and VR/AR in recent years, SLAM technology is well known and is considered one of the key technologies in these fields.

SLAM (Simultaneous Localization and Mapping), synchronous positioning and map construction, first proposed in the field of robots, it refers to: the robot starts from an unknown location of the unknown environment, and locates its position and posture through repeated observation of environmental characteristics during the movement. And then build an incremental map of the surrounding environment according to its own location, so as to achieve the purpose of simultaneous positioning and map construction. Due to the important academic value and application value of SLAM, it has always been considered as the key technology to realize fully autonomous mobile robots.

As the following picture, in general, SLAM answers two questions: "Where am I?" "What is it around me?" Just as people are in an unfamiliar environment, what SLAM tries to solve is to recover the observer itself and The relative spatial relationship of the surrounding environment, "Where am I?" corresponds to the positioning problem, and "what is around me" corresponds to the construction problem, giving a description of the surrounding environment. Answering these two questions, in fact, completed the spatial cognition of themselves and the surrounding environment. With this foundation, you can carry out path planning to reach the destination you want to go. In the process, you need to detect the obstacles encountered in time to ensure safe operation. "

Figure from DSO

 

---

The contents include -

1. SLAM technology

2. Introduction to SLAM Development

(1) Development of Lidar SLAM

(2) Visual SLAM development

(3) Several representative SLAM systems in the development of visual SLAM

3. Key issues in the visual SLAM system

(1) Use of image information

(2) Data association

(3) Initialization

(4) pose estimation

(5) Map construction

(6) Relocation

(7) Loopback detection

4. DLAM implementation difficulties

5. The future of SLAM

(1) Multi-sensor fusion SLAM

(2) Semantic SLAM