[논문]Predicting the internal model of a robotic system from its morphology

Duran, Angel J.; del Pobil, Angel P.

doi:10.1016/j.robot.2018.08.014

Predicting the internal model of a robotic system from its morphology 원문보기

Robotics and autonomous systems, v.110, 2018년, pp.33 - 43

Duran, Angel J. (Corresponding author.) , del Pobil, Angel P.

Abstract ▼ AI-Helper

Abstract The estimation of the internal model of a robotic system results from the interaction of its morphology, sensors and actuators, with a particular environment. Model learning techniques, based on supervised machine learning, are widespread for determining the internal model. An important limitation of such approaches is that once a model has been learnt, it does not behave properly when the robot morphology is changed. From this it follows that there must exist a relationship between them. We propose a model for this correlation between the morphology and the internal model parameters, so that a new internal model can be predicted when the morphological parameters are modified. Different neural network architectures are proposed to address this high dimensional regression problem. A case study is analyzed in detail to illustrate and evaluate the performance of the approach, namely, a pan–tilt robot head executing saccadic movements. The best results are obtained for an architecture with parallel neural networks. Our results can be instrumental in state-of-the-art trends such as self-reconfigurable robots, reproducible research, cyber–physical robotic systems or cloud robotics, in which internal models would available as shared knowledge, so that robots with different morphologies can readily exhibit a particular behavior in a given environment. Highlights A model to correlate the morphology and internal model parameters for a robotic system is presented. Different neural network architectures are proposed to solve this regression problem. A case study is used to illustrate and evaluate the neural network proposed. Due to the properties of the maximum likelihood estimator, the best performance is reached with parallel neural network architectures.

주제어

참고문헌 (38)

Science Bongard 314 5802 1118 2006 10.1126/science.1133687 Resilient machines through continuous self-modeling

상세보기
Vaughan 298 2006 From Animals to Animats, vol. 9 Use your illusion: Sensorimotor self-simulation allows complex agents to plan with incomplete self-knowledge
Robot. Auton. Syst. Sigaud 59 12 1115 2011 10.1016/j.robot.2011.07.006 On-line regression algorithms for learning mechanical models of robots: A survey

상세보기
Isidori 1 2003 Robust Autonomous Guidance Fundamentals of internal-model-based control theory
Cognit. Process. Nguyen-Tuong 12 4 319 2011 10.1007/s10339-011-0404-1 Model learning for robot control: a survey

상세보기
Siciliano 2008 Robotics: Modelling, Planning and Control
Science Pfeifer 318 November 1088 2007 10.1126/science.1145803 Self-organization, embodiment, and biologically inspired robotics

상세보기
Hudson 2000 IEEE Press Series in Biomedical Engineering Neural networks and artificial intelligence for biomedical engineering
IEEE Robot. Autom. Mag. Bonsignorio 22 3 32 2015 10.1109/MRA.2015.2452073 Toward replicable and measurable robotics research [from the guest editors]

상세보기
Robot. Auton. Syst. Felip 61 3 283 2013 10.1016/j.robot.2012.11.010 Manipulation primitives: A paradigm for abstraction and execution of grasping and manipulation tasks

상세보기
IEEE Syst. J. Khaitan 9 2 350 2015 10.1109/JSYST.2014.2322503 Design techniques and applications of cyberphysical systems: A survey

상세보기
A.P. del Pobil, Robots as cyberphysical systems: The challenges ahead, in: Keynote Speech at the 12th ACM International Conference on Ubiquitous Information Management and Communication, Langkawi, Malaysia, 2018.
Hermann 3928 2016 System Sciences (HICSS), 2016 49th Hawaii International Conference on Design principles for industrie 4.0 scenarios
IEEE Access Wan 4 2797 2016 Cloud robotics: Current status and open issues

상세보기
IEEE Trans. Autom. Sci. Eng. Kehoe 12 2 398 2015 10.1109/TASE.2014.2376492 A survey of research on cloud robotics and automation

상세보기
IEEE Robot. Autom. Mag. Waibel 18 2 69 2011 10.1109/MRA.2011.941632 Roboearth

상세보기
IEEE Access L’Heureux 5 7776 2017 10.1109/ACCESS.2017.2696365 Machine learning with big data: Challenges and approaches

상세보기
IEEE Trans. Robot. Autom. Rucci 15 1 96 1999 10.1109/70.744606 Adaptation of orienting behavior: from the barn owl to a robotic system

상세보기
Robot. Auton. Syst. Rucci 30 1 181 2000 10.1016/S0921-8890(99)00071-8 Robust localization of auditory and visual targets in a robotic barn owl

상세보기
Adv. Robot. Rucci 21 10 1115 2007 10.1163/156855307781389428 Integrating robotics and neuroscience: Brains for robots, bodies for brains

상세보기
Robot. Auton. Syst. Antonelli 71 13 2015 10.1016/j.robot.2014.11.018 Learning the visual-oculomotor transformation: Effects on saccade control and space representation

상세보기
Kawato 365 1990 Advanced Neural Computers Feedback-error-learning neural network for supervised motor learning
10.1109/ROBIO.2009.4913101 R. Saegusa, G. Metta, G. Sandini, S. Sakka, Active motor babbling for sensorimotor learning, in: IEEE International Conference on Robotics and Biomimetics, 2008, pp. 794-799, http://dx.doi.org/10.1109/ROBIO.2009.4913101.
Rahimi 1177 2007 Advances in Neural Information Processing Systems Random features for large-scale kernel machines
Neural Netw. Gijsberts 41 59 2013 10.1016/j.neunet.2012.08.011 Real-time model learning using incremental sparse spectrum gaussian process regression

상세보기
J. Statist. Plann. Inference Kohler 139 4 1286 2009 10.1016/j.jspi.2008.07.012 Optimal global rates of convergence for nonparametric regression with unbounded data

상세보기
Neural Netw. Møller 6 525 1993 10.1016/S0893-6080(05)80056-5 A scaled conjugate gradient algorithm for fast supervised learning supervised learning

상세보기
ICML Unsupervised Transf. Learn. Baldi 37 2012 Autoencoders, unsupervised learning, and deep architectures
Icml Rifai 85 1 833 2011 Contractive auto-encoders : Explicit invariance during feature extraction
Science Holden 313 July 504 2006 Reducing the dimensionality of data with neural networks
CS294A Lecture Notes Ng 72 1 2011 Sparse autoencoder
Int. J. Mach. Learn. Cybern. Meng 8 5 1719 2017 10.1007/s13042-016-0550-y Research on denoising sparse autoencoder

상세보기
Adv. Neural Inf. Process. Syst. Bengio 19 1 153 2007 Greedy layer-wise training of deep networks
Hastie 2009 The Elements of Statistical Learning: Data Mining, Inference, and Prediction
J. Amer. Statist. Assoc. Ye 93 441 120 1998 10.1080/01621459.1998.10474094 On measuring and correcting the effects of data mining and model selection

상세보기
Neural Netw. Anders 12 2 309 1999 10.1016/S0893-6080(98)00117-8 Model selection in neural networks

상세보기
J. Amer. Statist. Assoc. Kadane 99 465 279 2004 10.1198/016214504000000269 Methods and criteria for model selection

상세보기
Burnham vol. 172 488 2002 Model Selection and Multimodel Inference: A Practical Information-Theoretic Approach

LOADING...

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Predicting the internal model of a robotic system from its morphology 원문보기

Abstract ▼ AI-Helper

주제어

참고문헌 (38)

이 논문을 인용한 문헌

연구과제 타임라인

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

Predicting the internal model of a robotic system from its morphology 원문보기

Abstract ▼ AI-Helper

주제어

참고문헌 (38)

이 논문을 인용한 문헌

연구과제 타임라인

전체(0) 논문(0) 특허(0) 보고서(0)

전체(0) 논문(0) 특허(0) 보고서(0)

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트