iological and Cognitive Foun of Intelligent Sensor Fusio
Robin Roberson Murphy · 1996
Sensor fusion is being increasingly viewed as an important perceptual activity in mobile robotics. While the po- tential benefits of sensor fusion have motivated much research, no general purpose method for accomplishing sensor fusion has emerged. This paper reviews the literature from the bioIogical and cognitive sciences in sensory integration and derives princi- ples for use in constructing intelligent sensor fusion systems. In particular, it presents psychophysical and nenrophysical studies on how sensor fusion is accomplished and cognitive models of associated activities, including optimization of sensing configura- tions, improvement of sensing quality, and filtering of noise. The Sensor Fusion Effects (SFX) architecture for robot navigation is also presented as one example of how these insights from the biological and computer science can be applied to robotic sensor fusion. Experimental results demonstrates the utility of the biological and cognitive insights, especially that of fusion modes. Other representative architectures for robotic sensor fusion are contrasted with the biological and cognitive principles.