Continuous Categories For a Mobile Robot

Autonomouas gents make frequent use of knowledgei n the form of categories -- categories of objects, human gestures, web pages, and so on. This paper describes a way for agents to learn such categories for themselves through interaction with the environment. In particular, the learning algorithm transforms raw sensor readings into clusters of time series that have predictive value to the agent. We address several issues related to the use of an uninterpreted sensory apparatus and show specific examples where a Pioneer I mobile robot interacts with objects in a cluttered laboratory setting.

[1]  J. Mandler.  How to build a baby: II. Conceptual primitives. , 1992, Psychological review.

[2]  Benjamin Kuipers,et al.  A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations , 1991, Robotics Auton. Syst..

[3]  Ashwin Ram,et al.  Continuous Case-Based Reasoning , 1997, Artif. Intell..

[4]  Alex Pentland,et al.  Task-Specific Gesture Analysis in Real-Time Using Interpolated Views , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  S. S. Culbert,et al.  Cognition and Categorization , 1979 .

[6]  J. H. Ward.  Hierarchical Grouping to Optimize an Objective Function , 1963 .

[7]  Paul R. Cohen,et al.  Learned models for continuous planning , 1999, AISTATS.

[8]  Benjamin Kuipers,et al.  Map Learning with Uninterpreted Sensors and Effectors , 1995, Artif. Intell..

[9]  Sridhar Mahadevan,et al.  Rapid Concept Learning for Mobile Robots , 2004, Machine Learning.

[10]  Jun Tani,et al.  Model-based learning for mobile robot navigation from the dynamical systems perspective , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[11]  Brian Everitt,et al.  Cluster analysis , 1974 .

[12]  Maja J. Mataric,et al.  Integration of representation into goal-driven behavior-based robots , 1992, IEEE Trans. Robotics Autom..

[13]  Eamonn J. Keogh.  Fast similarity search in the presence of longitudinal scaling in time series databases , 1997, Proceedings Ninth IEEE International Conference on Tools with Artificial Intelligence.

[14]  Eamonn J. Keogh,et al.  An Enhanced Representation of Time Series Which Allows Fast and Accurate Classification, Clustering and Relevance Feedback , 1998, KDD.

[15]  Paul R. Cohen,et al.  Concepts From Time Series , 1998, AAAI/IAAI.

[16]  Sridhar Mahadevan,et al.  Rapid Concept Learning for Mobile Robots , 1998, Auton. Robots.

[17]  George Lakoff,et al.  Women, Fire, and Dangerous Things , 1987 .

[18]  Andrew McCallum,et al.  Learning to Use Selective Attention and Short-Term Memory in Sequential Tasks , 1996 .

[19]  Wayne Iba,et al.  Learning to Classify Observed Motor Behavior , 1991, IJCAI.

[20]  Maja J. Matarić,et al.  Learning to Use Selective Attention and Short-Term Memory in Sequential Tasks , 1996 .

[21]  Thomas Schreiber,et al.  Classification of Time Series Data with Nonlinear Similarity Measures , 1997 .

[22]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[23]  Paul Gonsalves,et al.  Increasing agent autonomy in dynamic environments , 1998, AGENTS '98.

[24]  M. Rosenstein,et al.  Reconstruction expansion as a geometry-based framework for choosing proper delay times , 1994 .