This paper describes a system which locates and grasps parts from a pile. The system uses photometric stereo and binocu lar stereo as vision input tools. Photometric stereo is used to make surface orientation measurements. With this informa tion the camera field is segmented into isolated regions of a continuous smooth surface. One of these regions is then selected as the target region. The attitude of the physical ob ject associated with the target region is determined by histo graming surface orientations over that region and comparing them with stored histograms obtained from prototypical objects. Range information, not available from photometric stereo, is obtained by the PRISM binocular stereo system. A collision-free grasp configuration is computed and executed using the attitude and range data.
Get full access to this article
View all access options for this article.
References
1.
Bajcsy, R.1980, Miami Beach. Three-dimensional scene analysis , Proc. 5th ICPR. 1064-1074.
2.
Ballard, D.H., and Sabbah, D.1981, Vancouver. On shapes. Proc. 7th IJCAI ,607-612.
3.
Birk, J.R., Kelley, R.B., and Martins, H.A.S.1981. An orienting robot for feeding workpieces stored in bins . Trans. IEEE. SMC, Vol. SMC-11; No. 2, 151-180.
4.
Boissonnat, J.D.1982. Stable matching between a hand structure and an object silhouette. Trans IEEE. PAMI, Vol. PAMI-4; No. 6, 603-612.
5.
Bolles, R.C., Horand, P., and Hannah, M.J.1984. 3DPO: a three-dimensional parts orientation system . Proc. Int. Symp. Robotic Res. 1. Brady, M. and Paul, P., eds. 413-424. MIT Press.
6.
Brady, M.1982. Parts description and acquisition using vision . Proc. SPIE. Robot Vision: Vol. 336, 20-28.
7.
Brooks, R.1981. Symbolic reasoning among 3D models and 2D images . Artificial Intelligence, Vol. 17, No. 1-3: 285-348.
8.
Brou, P.1984. Using the Gaussian image to find the orientation of objects . Int. J. Robotics Res. Vol. 3, No. 4: 89-125.
9.
Coleman, E.N., and Jain, R.1981, Vancouver. Shape from shading for surfaces with texture and specularity. Proc. 7th IJCAI . 652-657.
10.
Do Carmo, 1976. Differential geometry of curves and surfaces . Englewood Cliffs, N.J.: Prentice-Hall .
11.
Hanafusa, H., and Asada, H.1977. Stable prehension by a robot hand with elastic fingers . Proc. 7th ISIR. 361-368.
12.
Horn, B.K.P.1975. Obtaining shape from shading information. The Psychology of Computer Vision. Winston, P. H., ed. 115-155. New York: McGraw-Hill.
Horn, B.K.P., Woodham, R.J., and Silver, W.M.1978. Determining shape and reflectance using multiple images. AI Memo No. 490. Cambridge; Massachusetts Institute of Technology, Artificial Intelligence Laboratory .
15.
Horn, B.K.P., and Sjoberg, R.W.1979. Calculating the reflectance map. Applied Optics. Vol. 18: 1770-1779.
16.
Horn, B.K.P.1983. Extended Gaussian images. AI Memo 740 . Cambridge: Massachusetts Institute of Technology, Artificial Intelligence Laboratory.
17.
Ikeuchi, K.1981 a, Vancouver. Recognition of 3D object using extended Gaussian image. Proc. 7th IJCAI. 595-600.
18.
Ikeuchi, K.1981b. Determining surface orientations of specular surfaces by using the photometric stereo method. Trans. IEEE on PAMI. Vol. PAMI-2, No. 6: 661-669.
19.
Ikeuchi, K.1983. Determining attitude of object from needle map using extended Gaussian image. AI Memo 714. Cambridge : Massachusetts Institute of Technology, Artificial Intelligence Laboratory.
20.
Ikeuchi, K., Horn, B., Nagata, S., Callahan, T., and Feingold, O.1983. Picking up an object from a pile of objects. AI Memo 726. Cambridge: Massachusetts Institute of Technology, Artificial Intelligence Laboratory.
21.
Also available as Proc. Int. Symp. Robotics Res. 1, Brady M. and Paul, R. P., eds: 139-162. Cambridge: MIT Press.
22.
Ikeuchi, K.1985. A vision system for bin-picking tasks guided by an interpretation tree from a CAD model. Inf. Processing Soc. Japan , CVWG-38-6. (Japanese).
23.
Little, J.1985. Recovering shapes and determining attitude from extended Gaussian image. Ph. D. Thesis. University of British Columbia, Department of Computer Science.
24.
Lozano-Perez, T.1976. The design of a mechanical assembly system. AI-TR-397 . Massachusetts Institute of Technology, Artificial Intelligence Laboratory.
25.
Lozano-Perez, T.1981. Automatic planning of manipulator transfer movements . Trans. Sys. Man, Cyber. IEEE SMC-11, 681-698.
26.
Lozano-Perez, T.1983. Spatial planning: a configuration space approach . Trans. Computers C-32 IEEE: 108-120.
27.
Marr, D., and Hildreth, E.1980. Theory of edge detection. Proc. R. Soc. Lond. B. Vol. 207: 187-217.
28.
Marr, D., and Poggio, T.1979. A computational theory of human stereo vision. Proc. R. Soc. Lond, B. Vol. 204: 301-328.
29.
Also available as AI Memo 451Massachusetts Institute of Technology, Artificial Intelligence Laboratory.
Also available as AI Memo 780. Massachusetts Institute of Technology, Artificial Intelligence Laboratory.
32.
Nishihara, H.K., and Larson, N.G.1981April. Towards a real time implementation of the Marr-Poggio stereo matcher. Proc. A.R.P.A Image Understanding Workshop , L. S. Baumann, ed. Science Applications, Inc.
33.
Nishihara, H.K., and Poggio, T.1984. Stereo vision for robotics. Proc. Int. Symp. Robotics Res. 1 : 439-505. Brady, M. and Paul, R. P., eds. Cambridge: MIT. Press.
34.
Silver, W.A.1980. Determining shape and reflectance using multiple images. MS Thesis. Cambridge: MIT, EECS .
35.
Smith, D.A.1979. Using enhanced spherical images for object representation. AI Memo 530, Massachusetts Institute of Technology, Artificial Intelligence Laboratory.
36.
Tsuji, S., and Nakamura, A.1975, Georgia, USSR. Recognition of an object in a stack of industrial parts. Proc. 4th IJCAI:811-818.
37.
Woodham, R.J.1978August. Photometric stereo: a reflectance map technique for determining surface orientation from a single view. SPIE 22nd Annual Tech. Symp., Image Understanding Systems and Industrial Applications , Vol. 155: 136-143.
38.
Woodham, R.J.1979. Reflectance map techniques for analyzing surface defects in metal casting. AI-TR-457. Massachusetts Institute of Technology, Artificial Intelligence Laboratory.
39.
Woodham, R.J.1980. Photometric method for determining surface orientation from multiple images. Optical Eng. Vol. 19, No. 1: Jan/Feb., 139-144.
