Toward an assembly plan from observation. I. Task recognition with polyhedral objects

The authors present the assembly-plan-from-observation (APO) method for robot programming. The APO method aims to build a system that has the capability of observing a human performing an assembly task, understanding the task based on the observation, and subsequently generating a robot program to achieve the same task. This paper focuses on the task recognition module (TRM), the main component of a complete APO system. The TRM recognizes object configurations before and after an assembly task, detects a configuration transition, and infers the assembly task that causes such a configuration transition. We assume that each assembly task aims to achieve a face contact relation between an object that has just been manipulated and the stationary environmental objects. We prepare abstract task models that associate transitions of face contact relations with assembly tasks that achieve such transitions. Next, we implement TRM in order to verify two issues: 1) that such a contact transition can be recovered from the output of the object recognizer; and 2) that given these relation transitions, it is possible to use the abstract task models to generate robot motion commands. >

[1]  Daniel E. Whitney,et al.  State Space Models of Remote Manipulation Tasks , 1969, IJCAI.

[2]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[3]  Russell H. Taylor,et al.  AL, a programming system for automation. , 1974 .

[4]  Ann Patricia Fothergill,et al.  Inferring the Positions of Bodies from Specified Spatial Relationships , 1974, Artif. Intell..

[5]  Russell H. Taylor,et al.  The synthesis of manipulator control programs from task-level specifications , 1976 .

[6]  Saburo Tsuji,et al.  Understanding a Simple Cartoon Film by a Computer Vision System , 1977, IJCAI.

[7]  Tomás Lozano-Pérez,et al.  LAMA: A Language for Automatic Mechanical Assembly , 1977, IJCAI.

[8]  Michael A. Wesley,et al.  AUTOPASS: An Automatic Programming System for Computer Controlled Mechanical Assembly , 1977, IBM J. Res. Dev..

[9]  Robin J. Popplestone,et al.  RAPT, A Language for Describing Assemblies , 1978 .

[10]  Ann Patricia Fothergill,et al.  An Interpreter for a Language for Describing Assemblies , 1980, Artif. Intell..

[11]  Tomás Lozano-Pérez,et al.  Automatic Planning of Manipulator Transfer Movements , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[12]  Russell H. Taylor,et al.  Automatic Synthesis of Fine-Motion Strategies for Robots , 1984 .

[13]  Robert H. Thibadeau,et al.  Artificial Perception of Actions , 1986, Cogn. Sci..

[14]  Matthew T. Mason,et al.  Mechanics and Planning of Manipulator Pushing Operations , 1986 .

[15]  Ralph W. Will,et al.  A flexible telerobotic system for space operations , 1987 .

[16]  Kunikatsu Takase,et al.  Representation and Control of Motion in Contact and Its Application to Assembly Tasks , 1988 .

[17]  Takeo Kanade,et al.  Towards automatic generation of object recognition programs , 1988 .

[18]  Randy C. Brost,et al.  Automatic Grasp Planning in the Presence of Uncertainty , 1988, Int. J. Robotics Res..

[19]  Takeo Kanade,et al.  Automatic generation of object recognition programs , 1988, Proc. IEEE.

[20]  Christian Laugier,et al.  Planning fine motion strategies by reasoning in the contact space , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[21]  Arthur C. Sanderson,et al.  A correct and complete algorithm for the generation of mechanical assembly sequences , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[22]  Tomomasa Sato,et al.  Motion Understanding for World Model Management of Telerobot , 1989 .

[23]  Kunikatsu Takase,et al.  Skill Based Manipulation System , 1990 .

[24]  Masayuki Inaba,et al.  Design and implementation of a system that generates assembly programs from visual recognition of human action sequences , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[25]  Arthur C. Sanderson,et al.  Assembly Sequence Planning , 1990, AI Mag..

[26]  Avinash C. Kak,et al.  Spar: A Planner that Satisfies Operational and Geometric Goals in Uncertain Environments , 1990, AI Mag..

[27]  Shinichi Hirai,et al.  Towards a symbolic-level force feedback: recognition of assembly process states , 1991 .

[28]  Katsushi Ikeuchi,et al.  Determining linear shape change: Toward automatic generation of object recognition programs, , 1991, CVGIP Image Underst..

[29]  Mark D. Wheeler,et al.  Towards a Vision Algorithm Compiler for Recognition of Partially Occluded 3-D Objects , 1992 .

[30]  Katsushi Ikeuchi,et al.  Towards An Assembly Plan From Observation: Part II: Correction Of Motion parameters Based On Fact Contact Constraints , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[31]  Norihiro Abe,et al.  Assembling Plan Generation From An Assembly Illustration , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[32]  Randall H. Wilson,et al.  Partitioning An Assembly For Infinitesimal Motions In Translation And Rotation , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[33]  Achim Schweikard,et al.  Assembling polyhedra with single translations , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[34]  Katsushi Ikeuchi,et al.  Grasp Recognition Using The Contact Web , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[35]  Katsushi Ikeuchi,et al.  Determination of motion breakpoints in a task sequence from human hand motion , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.