| Adaptive Multi- Modal Sensors (2008) | |||||||||||||||
Abstract | |||||||||||||||
| Real world applications of robotics and artificial intelligence sometimes require input from unknown environments (Pederson, 2001). For such cases an internal representation of the environment must be created onthe-fly. The use of multi- modal sensors allows general solutions to be used for various classes of unknown environments. By adaptively changing the modality of sensors it is possible to, in many cases, reduce the number of sensors necessary to adequately sense the environment, as well as reduce the amount of bandwidth used by sensors. Here we present a self- constructive approach to developing a multicellular artificial organism capable of adjusting sensor modalities based upon sensory input from a dynamic environment (Fig. 1). The results demonstrate the robustness of this system within an environment of which the organism has no a priori knowledge. Organism Design. The multi- cellular organism exists in a 2.5D lattice (Fig. 1a.), where the half dimension represents the ability of cells to stack. | |||||||||||||||
Publication details | |||||||||||||||
| |||||||||||||||