– Operation:
– Two sources of information: idiothetic and allothetic
– Idiothetic source: dead reckoning methods like wheel revolutions
– Allothetic source: robot sensors such as camera, lidar, or sonar
– Perceptual aliasing issue: different places perceived as the same
– 3D models generated using range imaging sensors or 3D scanners
– Map representation:
– Metric vs. topological map representation
– Metric framework: precise coordinates in a 2D space
– Topological framework: considers places and relations
– Probabilistic representations used to handle uncertainty
– Main methods: free space maps, object maps, and composite maps
– Map learning:
– Map learning tied to localization process
– Simultaneous localization and mapping (SLAM) is crucial
– Determining if robot is in a known or new environment
– Solutions: electric beacons, NFC, WiFi, VLC, Li-Fi, Bluetooth
– Incorporation of localization errors into the map is a challenge
– Path planning:
– Essential for robot navigation from point A to B
– Computational complexity of path planning algorithms
– Feasibility depends on map accuracy, robot localization, and obstacles
– Topological relation to shortest path problem in graph theory
– Real-time motion planning requires accurate maps and localization
– Robot navigation:
– Outdoor robots utilize GPS for navigation
– Indoor robots use floor plans and beacons
– Electric beacons aid in cost-effective robot navigation
– Real-time locating system (RTLS) for precise robot location
– Various technologies like Wi-Fi positioning system (WPS) used in navigation
This article needs additional citations for verification. (October 2018) |
Robotic mapping is a discipline related to computer vision and cartography. The goal for an autonomous robot is to be able to construct (or use) a map (outdoor use) or floor plan (indoor use) and to localize itself and its recharging bases or beacons in it. Robotic mapping is that branch which deals with the study and application of ability to localize itself in a map / plan and sometimes to construct the map or floor plan by the autonomous robot.
Evolutionarily shaped blind action may suffice to keep some animals alive. For some insects for example, the environment is not interpreted as a map, and they survive only with a triggered response. A slightly more elaborated navigation strategy dramatically enhances the capabilities of the robot. Cognitive maps enable planning capacities and use of current perceptions, memorized events, and expected consequences.
