Analogy and metareasoning: Cognitive strategies for robot learning
作者： Ashok K. Goel , Tesca Fitzgerald , Priyam Parashar
DOI: 10.1016/B978-0-12-820543-3.00002-X
关键词: Cognition 、 Context (language use) 、 Robot 、 Analogy 、 Cognitive science 、 Novelty 、 Robot learning 、 Analogical reasoning 、 Computer science
摘要: Abstract Robots share a conundrum central to all intelligence. Like humans, robots not only must address novel situations but also start from what they already know: how, then, can any robot deal with novelty? In this chapter, we examine two cognitive strategies for addressing novelty: analogy and metareasoning. Analogy addresses new problems in manner similar familiar problem; the problem is part of context problem. We show how may use learn small number initial demonstrations. However, analogical reasoning more generally do necessarily guarantee success an open, dynamic world. This brings metareasoning into play. recover failure; here, failure forms other direction, discuss these experiments learning inform development theories
sci-hub.st 参考文章(19)
Baris Akgun, Maya Cakmak, Karl Jiang, Andrea L. Thomaz, Keyframe-based Learning from Demonstration Method and Evaluation International Journal of Social Robotics. ,vol. 4, pp. 343- 355 ,(2012) , 10.1007/S12369-012-0160-0
Brenna D. Argall, Sonia Chernova, Manuela Veloso, Brett Browning, A survey of robot learning from demonstration Robotics and Autonomous Systems. ,vol. 57, pp. 469- 483 ,(2009) , 10.1016/J.ROBOT.2008.10.024
Kalesha Bullard, Baris Akgun, Sonia Chernova, Andrea L. Thomaz, Grounding action parameters from demonstration robot and human interactive communication. pp. 253- 260 ,(2016) , 10.1109/ROMAN.2016.7745139
Sonia Chernova, Andrea L. Thomaz, Robot Learning from Human Teachers Synthesis Lectures on Artificial Intelligence and Machine Learning. ,vol. 8, pp. 1- 121 ,(2014) , 10.2200/S00568ED1V01Y201402AIM028
Sonia Chernova, Manuela Veloso, Confidence-based policy learning from demonstration using Gaussian mixture models adaptive agents and multi-agents systems. pp. 233- ,(2007) , 10.1145/1329125.1329407
S. Chernova, M. Veloso, Interactive policy learning through confidence-based autonomy Journal of Artificial Intelligence Research. ,vol. 34, pp. 1- 25 ,(2009) , 10.1613/JAIR.2584
Jim Davies, Ashok K. Goel, Patrick W. Yaner, Proteus: Visuospatial analogy in problem-solving Knowledge Based Systems. ,vol. 21, pp. 636- 654 ,(2008) , 10.1016/J.KNOSYS.2008.03.035
Brian Falkenhainer, Kenneth D. Forbus, Dedre Gentner, The structure-mapping engine: Algorithm and examples Artificial Intelligence. ,vol. 41, pp. 1- 63 ,(1989) , 10.1016/0004-3702(89)90077-5
Tesca Fitzgerald, Ashok Goel, Andrea Thomaz, Human-Guided Object Mapping for Task Transfer human robot interaction. ,vol. 7, pp. 17- ,(2018) , 10.1145/3277905
Mary L. Gick, Keith J. Holyoak, Schema induction and analogical transfer Cognitive Psychology. ,vol. 15, pp. 1- 38 ,(1983) , 10.1016/0010-0285(83)90002-6