An Approach to Automatic Robot Programming Based on Inductive Learning

Abstract

Automatic programming of manipulator robots attracts in creasing interest within the context of mechanical assembly. In this paper we focus on the problem of mating two parts, which requires sensor-based strategies to deal with geometric uncertainty. We present a system that embodies a two-phase approach to build robot programs implementing such strate gies. First a training phase interacts with the robot actuators and sensors and produces traces of execution of a given part- mating operation. Next a purely computational induction phase transforms these traces into an executable manipula tor-level program for the operation. The system embedding this approach has been completely implemented, and it has been used experimentally on several assembly tasks.

Get full access to this article

View all access options for this article.

References

Ambler, A.P. , and Popplestone, R.J. 1975. Inferring the positions of bodies from specified spatial relationships. Artificial Intell. 6(2):157 -174.

Biermann, A.W. , and Krishnaswamy, R. 1976. Constructing programs from example computations. IEEE Trans. Software Eng. (2):141-153.

Brooks, R.A. 1982a. Solving the find-path problem by good representation of free space. Proc. 2nd Amer. Assoc. Artificial Intell. Conf, pp. 381-386.

Brooks, R.A. 1982b. Symbolic error analysis and robot planning. Int. J. Robotics Res. 1(4):29-68.

Dufay, B. , and Laugier, C. 1983. Geometrical reasoning in automatic grasping and contact analysis. Advances in CAD/CAM, ed. T. M. R. Ellis and O. I. Semenkov. New York: North Holland, pp. 473-482.

Dufay, B. 1983. Apprentissage par induction en robotique: Application à la synthèse de programmes de montage. Thesis, National Polytechnic Institute of Grenoble.

Dufay, B. , and Latombe, J.C. 1983 (Bretton Woods, N.H.). An approach to automatic robot programming based on inductive learning. Proc. 1st Int. Symp. Robotics Res. Cambridge: MIT Press.

Fikes, R.E. , Hart, P.E. , and Nilsson, N.J. 1972. Learning and executing generalised robot plans. Artificial Intell., vol. 3, pp. 251-288.

Fu, K.S. , and Booth, L.T. 1975. Grammatical inference: Introduction and survey. IEEE Trans. on S.M.C. 5(1):95- 111; 5(4):409-423.

10.

Latombe, J.C. 1982a. Equipe intelligence artificielle et robotique: Etat d'advancement des recherches au Ier Octobre 1981. Tech. Rept. 291. Saint-Martin-d'Heres , France: IMAG Laboratory.

11.

Latombe, J.C. 1982b. Survey of advanced general-purpose software for robot manipulators. Computers in Industry. 4(3):227-242.

12.

Latombe, J.C. , and Mazer, E. 1981. LM: A high-level programming language for controlling manipulators. Proc. 11th Int. Symp. Industr. Robots . Tokyo: JIRA, pp. 683-690.

13.

Laugier, C. 1981. A program for automatic grasping of objects with a robot arm. Proc. 11th Int. Symp. Industr. Robots. Tokyo: JIRA, pp. 287-294.

14.

Laugier, C. , and Pertin, J. 1983. Automatic grasping: A case study in accessibility analysis. Advanced software in robotics, ed. A. Danthine and M. Geradin. Amsterdam: North Holland, pp. 201-214.

15.

Lieberman, L.I. , and Wesley, M.A. 1977. AUTOPASS: An automatic programming system for computer controlled mechanical assembly. IBM J. Res. Dev., 21 (4):321- 333.

16.

Lozano-Pérez, T. 1976. The design of a mechanical assembly system. Rept. AI-TR-397 Cambridge: M.LT. Artificial Intelligence Laboratory.

17.

Lozano-Pérez, T. 1980. Automatic planning of manipulator transfer movements. Memo 606 Cambridge: M.I.T. Artifician Intelligence Laboratory.

18.

Lozano-Pérez, T. 1982. Task planning. Robot motion: Planning and control , ed. M. Brady et al. Cambridge: MIT Press , pp. 463-498.

19.

Lozano-Pérez, T. , Mason, M.T. , and Taylor, R.H. 1983 (Bretton Woods, N.H.). Automatic synthesis of fine motion strategies for robots. Proc. 1st Int. Symp. Robotics Res. Cambridge: MIT Press.

20.

Mazer, E. 1982. An algorithm for computing the relative position between two objects from symbolical specifications. Rept. 297. Saint-Martin-d'Heres, France: IMAG Laboratory.

21.

Mazer, E. 1983. Geometric programming of assembly robots (LM-GEO). Advanced software in robotics, ed. A. Danthine and M. Geradin. Amsterdam: North Holland, pp. 99-110.

22.

Mujtaba, S. , and Goldman, R. 1979. AL user's manual. Memo AI 323 Stanford, Calif.: Artificial Intelligence Laboratory.

23.

Naranjo, M. 1984. Commande et identification d'automates à partir d'informations incertaines. Thesis, University of Clermont-Ferrand.

24.

Oakey, S. , and Cawthorn, R.C. 1981 (Vancouver, B.C.). Inductive learning of pronunciation rules by hypothesis testing and correction. Proc. Int. Joint Conf Artificial Intell, pp. 109 -114.

25.

Selfridge, M. , and Levas, A. 1983 (Chicago). Teaching robots by example . Proc. 13th Int. Symp. Industr. Robots, pp. 160-165.

26.

Taylor, R.H. 1976. Synthesis of manipulator control programs from task level specifications. Memo AIM228 Stanford Calif.: Artifician Intelligence Laboratory.

27.

Taylor, R.H. , Summers, P.D. , and Meyer, J.M. 1982. AML: A manufacturing language. Int. J. Robotics Res. 1(3):19-41.

28.

Udupa, S.M. 1977 (Cambridge, Mass.). Collision detection and avoidance in computer controlled manipulators. Proc. Int. Joint. Conf Artificial Intellpp. 737-748.

29.

Wingham, M. 1977. Planning how to grasp objects in a cluttered environment. M.Phil. thesis, University of Edinburgh.

30.

Winston, P.H. 1975. Learning structural description from examples. The psychology of computer vision, ed. P. H. Winston. New York: McGraw-Hill, pp. 157-209.