Explanation-based learning for mobile-robot perception

Explanation-based neural network learning (EBNN) has recently been proposed as a method for reducing the amount of training data required for reliable generalization, by relying instead on approximate, previously learned knowledge. We present first experiments applying EBNN to the problem of learning object recognition for a mobile robot. In these experiments, a mobile robot traveling down a hallway corridor learns to recognize distant doors based on color camera images and sonar sensations. The previously learned knowledge corresponds to a neural network that recognizes nearby doors, and a second network that predicts the state of the world after travelling forward in the corridor. Experimental results show that EBNN is able to use this approximate prior knowledge to significantly reduce the number of training examples required to learn to recognize distant doors. We also present results of experiments in which networks learned by EBNN (e.g., "there is a door 2 meters ahead") are then used as background knowledge for learning subsequent functions (e.g., "there is a door 3 meters ahead").

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  Yann LeCun,et al.  Tangent Prop - A Formalism for Specifying Selected Invariances in an Adaptive Network , 1991, NIPS.

[3]  Rich Caruana,et al.  Learning Many Related Tasks at the Same Time with Backpropagation , 1994, NIPS.

[4]  Dean A. Pomerleau,et al.  Neural Network Perception for Mobile Robot Guidance , 1993 .

[5]  Michael Hucka,et al.  Learning in Tele-autonomous Systems using Soar , 1989 .

[6]  Sebastian Thrun,et al.  Explanation-based neural network learning , 1996 .

[7]  Sridhar Mahadevan,et al.  Scaling Reinforcement Learning to Robotics by Exploiting the Subsumption Architecture , 1991, ML.

[8]  Andrew W. Moore,et al.  Efficient memory-based learning for robot control , 1990 .

[9]  Lorien Y. Pratt,et al.  Experiments on the transfer of knowledge between neural networks , 1994, COLT 1994.

[10]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[11]  Long-Ji Lin,et al.  Reinforcement learning for robots using neural networks , 1992 .

[12]  Jude Shavlik,et al.  An Approach to Combining Explanation-based and Neural Learning Algorithms , 1989 .

[13]  Fu,et al.  Integration of neural heuristics into knowledge-based inference , 1989 .

[14]  Sebastian Thrun,et al.  Learning One More Thing , 1994, IJCAI.

[15]  Tom Michael Mitchell,et al.  Explanation-based generalization: A unifying view , 1986 .

[16]  Susan L. Epstein.  For the Right Reasons: The FORR Architecture for Learning in a Skill Domain , 1994, Cogn. Sci..

[17]  Rodney A. Brooks,et al.  Learning to Coordinate Behaviors , 1990, AAAI.

[18]  Tom Michael Mitchell.  Learning Analytically and Inductively , 1995 .

[19]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[20]  Sebastian Thrun,et al.  Lifelong robot learning , 1993, Robotics Auton. Syst..

[21]  Katsushi Ikeuchi,et al.  Towards an assembly plan from observation : fine localization based on face contact constraints , 1991 .

[22]  Sebastian Thrun,et al.  Active Exploration in Dynamic Environments , 1991, NIPS.

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

[24]  David Haussler,et al.  Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications , 1992, Inf. Comput..

[25]  B. Efron.  The jackknife, the bootstrap, and other resampling plans , 1987 .

[26]  Sridhar Mahadevan,et al.  Enhancing Transfer in Reinforcement Learning by Building Stochastic Models of Robot Actions , 1992, ML.

[27]  李幼升,et al.  Ph , 1989 .

[28]  Raymond J. Mooney,et al.  Combining Neural and Symbolic Learning to Revise Probabilistic Rule Bases , 1992, NIPS.

[29]  Sebastian Thrun,et al.  Integrating Inductive Neural Network Learning and Explanation-Based Learning , 1993, IJCAI.

[30]  Sridhar Mahadevan,et al.  Rapid Task Learning for Real Robots , 1993 .

[31]  J. Shavlik,et al.  Re nement of Approximate Domain Theories byKnowledge-Based Neural Networks , 1990 .