Real-time control of a mobile robot by using visual stimuli

We show that qualitative properties of optical flow fields suffice for realizing simple autonomous behaviours of a mobile robot in real-time. Such properties are derived by analyzing the motion components (expansion, rotation, X-Y translation and deformation), previously described by Subbarao (1990) and Cipolla (1992), for a local flow field. In particular, we show that such components can be reliably measured by translation invariant, linear and uncalibrated detectors, each one tuned on a particular motion component. The main difference between our scheme and the one proposed by Cipolla is that ours does not require any physical contour to be tracked for inferring qualitative properties of the perceived optical flow. Moreover, the measurement of the affine transformation coefficients does not involve any matrix inversion. The responses of the proposed motion component tuned detectors, expressed in terms of their relative excitation to the perceived visual stimulus, are used as controlled signals in closed feedback loop controllers, working in real-time (12.5 Hz), for realizing three types of opto-motor reflexes