The Importance of Mapping in Robotics
We humans navigate new environments on a regular basis. Within moments we’re capable of identifying objects, planning movement, and assessing context such as the weather. This is all possible due to the acuity of our natural senses, and our brain’s ability to fuse this information on the fly.
Truly, one of the most humbling aspects of bringing intelligence to inanimate objects — which is what we, as roboticists, are committed to achieving! — is realizing how much we humans take for granted with regards to our ability to perceive, orient, and process information.
As we build intelligent robots, and program them to understand their environments, we have to engineer a similar ability deliberately into our creations. In Robotics we call this “Map Building” or simply “Mapping.”
As a robot navigates its environment, it must compose a data model or “map” of its surroundings, using data from available sensors. This map is the robotic equivalent of what we might call a picture in our mind’s eye. But whereas our human “map” draws on sensory information, a robot relies on data fused from depth cameras and/or LIDAR using the SLAM algorithm (which we’ll be covering in detail in Term 2 of the Robotics Nanodegree program!). Depending on the capabilities of the sensor, the robot’s map could be in 2D or 3D.
As an aspiring roboticist, you’re going to find that mapping is critical in almost every problem you’re trying to solve. For that reason, we provide a number of opportunities throughout the Robotics Nanodegree program for you to apply mapping techniques to your projects. Whether it be generating a 2D map to help a rover navigate unknown terrain, or composing a 3D map (using Octomaps) to enable a robotic arm to isolate objects on a shelf, you’ll experience firsthand what mapping makes possible — intelligent robots that assess their environment on the fly, just like we do.
