Map learning with uninterpreted sensors and effectors
Artificial Intelligence
| Hi-index | 0.00 |
A baby experiencing the world for the first time faces a considerable challenging sorting through what William James called the "blooming, buzzing confusion" of the senses. With the increasing capacity of modern sensors and the complexity of modern robot bodies, a robot in an unknown or unfamiliar body faces a similar and equally daunting challenge. Addressing this challenge directly by designing robot agents capable of resolving the confusion of sensory experience in an autonomous manner would substantially reduce the engineering required to program robots and the improve the robustness of resulting robot capabilities. Working towards a general solution to this problem, this work uses distinctive state abstractions and sensorimotor embedding to generate basic knowledge of sensor structure, local geometry, and object geometry starting with uninterpreted sensors and effectors.