MODEL-BASED PLANNING OF OPTIMAL SENSOR PLACEMENTS FOR INSPECTION

We report a system for sensor planning, GASP, which is used to compute the optimal positions for inspection tasks using known imaging sensor s and feature-based object models. GASP (general automatic sensor plan ning) uses a feature inspection representation (the FIR), which contai ns the explicit solution for the simplest sensor positioning problem. The FIR is generated off-line, and is exploited by GASP to compute on- line plans for more complex tasks, called inspection scripts. Viewpoin t optimality is defined as a function of feature visibility and measur ement reliability. Visibility is computed using an approximate model. Reliability of inspection depends on both the physical sensors acquiri ng the images and on the processing software; therefore we include bot h these components in a generalized sensor model. These predictions ar e based on experimental, quantitative assessment. We show how these ar e computed for a real generalized sensor, which includes a 3-D range i maging system, and software performing robust outlier removal, surface segmentation, object location and surface fitting. Finally, we demons trate a complete inspection session involving 3-D object positioning, planning optimal position inspection, and feature measurement from the optimal viewpoint.