Experience-Based Generation of Maintenance and Achievement Goals on a Mobile Robot

Abstract Learning skills or knowledge online from experiences is attractive for robots because it permits them to develop new behavior autonomously. However, the onus lies with the system designer to specify which skills or knowledge the robot should learn. Experience-based goal generation algorithms permit a robot to decide autonomously what it will to learn. This paper presents an adaptive resonance theory approach to experience-based generation of approach, avoidance, maintenance and achievement goals for a mobile robot. An experimental analysis is conducted to explore the relationship between algorithm parameters and goals generated on a simulated ePuck robot. Results show how parameter choice influences the number, stability and nature of generated goals. We identify theweight representations, distance functions and update rules that are appropriate for a mobile robot to generate maintenance and achievement goals.

[1]  Pierre-Yves Oudeyer,et al.  Maturationally-constrained competence-based intrinsically motivated learning , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[2]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[3]  Ethem Alpaydin,et al.  Simplified ART: A new class of ART algorithms , 1998 .

[4]  A. Pentland,et al.  Artificial intelligence. Autonomous mental development by robots and animals. , 2001, Science.

[5]  Stephen R. Marsland,et al.  On-line novelty detection for autonomous mobile robots , 2005, Robotics Auton. Syst..

[6]  Pierre-Yves Oudeyer,et al.  Intrinsically motivated goal exploration for active motor learning in robots: A case study , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[8]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[9]  Pierre-Yves Oudeyer,et al.  Motivational principles for visual know-how development , 2003 .

[10]  Stephen Grossberg,et al.  ART 3: Hierarchical search using chemical transmitters in self-organizing pattern recognition architectures , 1990, Neural Networks.

[11]  Kathryn E. Merrick,et al.  Reasoning in the Absence of Goals , 2011, AAAI Fall Symposium: Advances in Cognitive Systems.

[12]  Michael Barlow,et al.  Self-motivated learning of achievement and maintenance tasks for non-player characters in computer games , 2014, 2014 IEEE Symposium on Computational Intelligence for Human-like Intelligence (CIHLI).

[13]  Pierre-Yves Oudeyer,et al.  Active learning of inverse models with intrinsically motivated goal exploration in robots , 2013, Robotics Auton. Syst..

[14]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[15]  Kathryn E. Merrick,et al.  Modeling Behavior Cycles as a Value System for Developmental Robots , 2010, Adapt. Behav..

[16]  Nuttapong Chentanez,et al.  Intrinsically Motivated Reinforcement Learning , 2004, NIPS.

[17]  Kathryn E. Merrick,et al.  Motivated Reinforcement Learning - Curious Characters for Multiuser Games , 2009 .

[18]  B Fritzke,et al.  A growing neural gas network learns topologies. G. Tesauro, DS Touretzky, and TK Leen, editors , 1995, NIPS 1995.

[19]  Kathryn E. Merrick,et al.  A Comparative Study of Value Systems for Self-Motivated Exploration and Learning by Robots , 2010, IEEE Transactions on Autonomous Mental Development.

[20]  Tirtharaj Dash,et al.  Automatic navigation of wall following mobile robot using Adaptive Resonance Theory of Type-1 , 2015, BICA 2015.

[21]  Raúl Rojas.  Unsupervised Learning and Clustering Algorithms , 1996 .

[22]  Daniel Moldt,et al.  Goal Representation for BDI Agent Systems , 2004, PROMAS.

[23]  Rob Saunders,et al.  Curious Design Agents and Artificial Creativity - A Synthetic Approach to the Study of Creative Behaviour , 2001 .

[24]  S. Grossberg,et al.  ART 2: self-organization of stable category recognition codes for analog input patterns. , 1987, Applied optics.

[25]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[26]  S. Grossberg,et al.  Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors , 1976, Biological Cybernetics.

[27]  Andrew G. Barto,et al.  Causal Graph Based Decomposition of Factored MDPs , 2006, J. Mach. Learn. Res..

[28]  Andrew G. Barto,et al.  Skill Characterization Based on Betweenness , 2008, NIPS.

[29]  Anand S. Rao,et al.  BDI Agents: From Theory to Practice , 1995, ICMAS.

[30]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[31]  Marco Mirolli,et al.  Which is the best intrinsic motivation signal for learning multiple skills? , 2013, Front. Neurorobot..

[32]  S. Chumkamon,et al.  Intelligent emotion and behavior based on topological consciousness and adaptive resonance theory in a companion robot , 2016, BICA 2016.

[33]  Kathryn E. Merrick.  Modelling Affordances for the Control and Evaluation of Intrinsically Motivated Robots , 2009 .

[34]  Richard S. Sutton,et al.  Scaling life-long off-policy learning , 2012, 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[35]  Kathryn E. Merrick,et al.  Task allocation in multi-agent systems using models of motivation and leadership , 2012, 2012 IEEE Congress on Evolutionary Computation.