Knowledge Representation for Robot Vision and Path Planning Using Attributed Graphs and Hypergraphs
Abstract
This paper presents a general and flexible knowledge representation system using attributed graph representation (AGR) and attributed hypergraph representation (AHR) as the basic data structure. Based on these representations, object recognition and interpretation can be achieved by a hypergraph monomorphism algorithm and a knowledge directed search procedure. A graph synthesis procedure is used to combine the AGR’s or AHR’s obtained from images of different views of an object into a unique AHR. For recognition and location of 3-D objects in 2-D perspective images, another form of AHR, known as Point Feature Hypergraph Representation (PHR) is introduced. With PHR, a constellation matching algorithm can be used to compare images and models as well as to derive 3-D information from stereoscopic images. From the PHR of 3-D objects, procedural knowledge can be formulated and used to search for features in a 2-D perspective image for the recognition and location of 3-D objects in 2-D images. Further, the AGR can also be used to represent the geometric and topological information of the world environment of a mobile robot. A special search algorithm converts the AGR into a AHR from which a compact road map is derived for path and trajectory planning as well as navigation. The proposed method renders greater tolerance to local scene changes.
Keywords
Mobile Robot Point Feature Path Planning Procedural Knowledge Search ActivationPreview
Unable to display preview. Download preview PDF.
References
- 1.Barnard, S.T., “Interpreting Perspective Images”, Artificial Intelligence 21, 1983.Google Scholar
- 2.Berge, C., “Graphs and Hypergraphs”, North-Holland Publishing Company, Amsterdam.Google Scholar
- 3.Besl, P.J. and Jain, R.C., “Three-Dimensional Object Recognition”, Computing Survey, Vol. 17, No. 1, pp. 75–145, March 1985.CrossRefGoogle Scholar
- 4.Binford, T.O., ‘Visual Perceptions by Computer’’, IEEE Conf. on Systems and Control, Miami, Dec. 1971.Google Scholar
- 5.Brooks, R.A., “Symbolic Reasoning Among 3-D Models and 2-D Images”, Artificial Intelligence, 17, 1981.Google Scholar
- 6.Brooks, R.A., “Solving the Find-Path Problem by Good Representation of Free Space”, IEEE Trans. on Systems, Man and Cybernetics, Vol. SMC-13, No. 3, March/April 1983.Google Scholar
- 7.Bugihara, K., “An Algebraic Approach to Shape-from-Image Problems”, Artificial Intelligence, 23, 1984.Google Scholar
- 8.Giralt, G., Chatila, R. and Vaisset, M., “An Integrated Navigation and Motion Control System for Autonomous Multisensory Mobile Robots”, First International Symposium on robotics Research, The MIT Press, Cambridge, Massachusetts, 1983.Google Scholar
- 9.Grahraman, D.E., Wong, A.K.C., and Au, T., “Graph Monomorphism Algorithms”, IEEE Trans. on Systems, Man and Cybernetics, Vol. SMC-10, No. 4, pp. 181–189, 1980.CrossRefGoogle Scholar
- 10.Jackin, Tanimoto, “Oct-trees and Their Use in Representing ThreeDimmensional Objects’’, CGIP, 14, pp. 249–270, 1980.Google Scholar
- 11.Langeland, N.J., “Reconstruction of 3-D Objects from 2-D Image”, The Norwegian Institute of Technology, Trondheim, January 1984.Google Scholar
- 12.Lee, S.J., Haralick, R.M., and Zhang, M.C., “Understanding Objects with Curved Surfaces from a Single Perspective View of Boundaries”, Artificial Intelligence 26, 1985.Google Scholar
- 13.Lu, S.W., Wong, A.K.C., and Riuox, M., ‘Recognition of 3-D Objects in Range Images by Attributed Hypergraph Monomorphism and Synthesis’’, Proc. of International Symposium on New Directions in Computing, pp. 389–394, 1985.Google Scholar
- 14.Requicha, A.A.G., “Representation of rigid Solid Objects”, Computer Survey, 12.4, pp. 437–464, 1980.Google Scholar
- 15.Rosenfeld, A., “Image Analysis: Problems, Progress and Prospects”, Pattern Recognition, Vol. 17, No. 1, pp. 3–12, January 1984.CrossRefGoogle Scholar
- 16.Rueb K.D., and Wong, A.K.C., Analysis of Point Feature Representation of a Perspective Image, Internal Report, Systems Design Engineering, University of Waterloo, 1986.Google Scholar
- 17.Rueb K.D. and Wong, A.K.C., “Structuring Free Space as a Hypergraph for Roving Robot Path Planning and Navigation”, to appear in IEEE Trans. on PAM! 1987.Google Scholar
- 18.Voelcker, H.B., and Requicha, A.A.G., “Geometric Modelling of Mechanical Parts and Processes”, Computer, 10, pp. 48–57, 1977.CrossRefGoogle Scholar
- 19.Wong, A.K.C., Lu, S.W., and M. Riuox, “Recognition and Knowledge Synthesis of 3-D Object Images based on Attributed Hypergraphs”, Internal Report, Systems Design Engineering, University of Waterloo, 1986.Google Scholar
- 20.Wong, A.K.C., and Salay, R., “An Algorithm for Constellation Matching Proc. of the 8th International Conf. on Pattern Recognition, Paris, pp. 546–554, 1986.Google Scholar
- 21.Akinniyi, F.A., Wong, A.K.C. and Stacey, D.A., “A New Algorithm for Graph Monomorphism based on the Projections of the Product Graph”, IEEE Trans. on SMC, Vol. SMC-16, No. 5, pp. 740–751, September, 1986.Google Scholar
- 22.Wong, A.K.C., and Akinniyi, F.A., “An Algorithm for the Largest Common Subgraph Isomorphism Using the Implicit Net”, IEEE Proc. of the International Conference on Systems, Man and Cybernetics, Bombay, 1983, pp. 197–201.Google Scholar
- 23.Wong, A.K.C., and You, M., entropy and Distance of Random Graphs With Application to Structural Pattern Recognition“, IEEE. Trans. on Pattern Analysis and Machine Intelligence, Vol. PAMI-7, NO. 5, pp. 599–607, September 1985.CrossRefGoogle Scholar