Simultaneous localization and mapping (SLAM) is the synchronous location awareness and recording of the environment in a map of a computer, device, robot, drone or other autonomous vehicle. SLAM is a key component in self-driving vehicles and other autonomous robots enabling awareness of where they are and the best routes to where they are going. By creating its own maps, SLAM enables quicker, more autonomous and adaptable response than pre-programmed routes.
A number of emitters and sensors work together in sensor fusion with an AI for a single purpose in SLAM. A robot that uses SLAM, for example, employs various types of cameras and sensors such as radar, Lidar, ultrasonic and other technologies to understand its environment. By better understanding its environment, a robot can more effectively map, navigate, avoid obstacles and adjust to changes.
Highly accurate GPS modules have reduced the need for SLAM in some applications. High-precision GPS can almost entirely replace SLAM in some outdoor environments. That said, GPS may suffer reduced performance or outages, and SLAM can fill in the gaps in navigation where more detail is needed and also take over in the case of these difficulties.