ok, moving object detected and is stationary. What next? A video camera can be used. An open source program like this can be used : http://dorgem.sourceforge.net/ Focal point of lens can be used for depth perception (perspective) Then you can code the screen pixels such that the extreme left top is (x,y) 0'0 and Z being a variable - etc a) Calculate position X,Y,Z ( grid based ) b) approach target c) redetect target - or update target d) approach target (by avoiding obstacles) e) redetect target f) approach target (its a loop) e) identify target f) determine cause of action Its a dumb system, because if the target becomes stationary ; then the code will deem it as part of background... Unless one has a memory bank that 'remembers' bearing and shape of the scanned object - even if the pursuing object changes direction to avoid obstacles...