Learning Concepts from Sensor Data of a Mobile Robot

Machine learning can be a most valuable tool for improving the flexibility and efficiency of robot applications. Many approaches to applying machine learning to robotics are known. Some approaches enhance the robot's high-level processing, the planning capabilities. Other approaches enhance the low-level processing, the control of basic actions. In contrast, the approach presented in this paper uses machine learning for enhancing the link between the low-level representations of sensing and action and the high-level representation of planning. The aim is to facilitate the communication between the robot and the human user. A hierarchy of concepts is learned from route records of a mobile robot. Perception and action are combined at every level, i.e., the concepts are perceptually anchored. The relational learning algorithm GRDT has been developed which completely searches in a hypothesis space, that is restricted by rule schemata, which the user defines in terms of grammars.

[1]  F. Jelinek,et al.  Continuous speech recognition by statistical methods , 1976, Proceedings of the IEEE.

[2]  Luc Steels,et al.  Building agents out of autonomous behavior systems , 1995 .

[3]  Scott William Bennett.  Learning Uncertainty Tolerant Plans through Approximation in Complex Domains , 1989 .

[4]  L. D. Raedt.  Interactive theory revision: an inductive logic programming approach , 1992 .

[5]  Saso Dzeroski,et al.  PAC-learnability of determinate logic programs , 1992, COLT '92.

[6]  Sebastian Thrun,et al.  Explanation-Based Neural Network Learning for Robot Control , 1992, NIPS.

[7]  Tom M. Mitchell,et al.  Becoming Increasingly Reactive , 1990, AAAI.

[8]  Rüdiger Dillmann,et al.  PRIAMOS: An experimental platform for reflexive navigation , 1993, Robotics Auton. Syst..

[9]  David Atkinson,et al.  Generating Perception Requests and Expectations to Verify the Execution of Plans , 1986, AAAI.

[10]  Rodney A. Brooks,et al.  The role of learning in autonomous robots , 1991, COLT '91.

[11]  Nils J. Nilsson,et al.  Shakey the Robot , 1984 .

[12]  G. Plotkin.  Automatic Methods of Inductive Inference , 1972 .

[13]  Birgit Tausend,et al.  Representing Biases for Inductive Logic Programming , 1994, ECML.

[14]  Francesco Bergadano,et al.  An Interactive System to Learn Functional Logic Programs , 1993, IJCAI.

[15]  Bonnie Webber,et al.  Animation from instructions , 1991 .

[16]  Jorg-uwe Kietz,et al.  Controlling the Complexity of Learning in Logic through Syntactic and Task-Oriented Models , 1992 .

[17]  Tim Lüth,et al.  Utilizing Spatial Relations for Natural Language Access to an Autonomous Mobile Agent , 1994, KI.

[18]  Yolanda Gil,et al.  Learning by Experimentation: Incremental Refinement of Incomplete Planning Domains , 1994, International Conference on Machine Learning.

[19]  J. Millán,et al.  A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze-Like Environments , 2004, Machine Learning.

[20]  Stefan Wrobel,et al.  Towards a Model of Grounded Concept Formation , 1991, IJCAI.

[21]  Leslie Pack Kaelbling,et al.  Action and planning in embedded agents , 1990, Robotics Auton. Syst..

[22]  J. Ross Quinlan,et al.  Learning logical definitions from relations , 1990, Machine Learning.

[23]  Gerald DeJong,et al.  Permissive Planning: A Machine Learning Approach to Linking Internal and External Worlds , 1993, AAAI.

[24]  Nicolas Helft,et al.  Induction as Nonmonotonic Inference , 1989, KR.

[25]  Stefan Wrobel.  Higher-order Concepts in a Tractable Knowledge Representation , 1987, GWAI.

[26]  Kai Zercher.  Wissensintensives Lernen für zeitkritische technische Diagnoseaufgaben , 1992, DISKI.

[27]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[28]  Wei-Min Shen.  Discovery as autonomous learning from the environment , 2004, Machine Learning.

[29]  William W. Cohen.  Grammatically Biased Learning: Learning Logic Programs Using an Explicit Antecedent Description Language , 1994, Artif. Intell..

[30]  Gerald DeJong,et al.  An Incremental Learning Approach for Completable Planning , 1994, ICML.