Deep learning in robotics: a review of recent research

Advanced Robotics

Volumn 31, Issue 16, 2017, Pages 821-835

  Pierson, Harry A ^a   Gashler, Michael S ^a  

^a University of Arkansas   (United States)

Author keywords

artificial intelligence; Deep neural networks; human robot interaction

Indexed keywords

ARTIFICIAL INTELLIGENCE; DEEP NEURAL NETWORKS; HUMAN ROBOT INTERACTION; INTELLIGENT ROBOTS; NEURAL NETWORKS; ROBOTICS;

PHYSICAL ROBOTIC SYSTEM; RECENT RESEARCHES; ROBOT INTERACTIONS; ROBOTIC SYSTEMS;

DEEP LEARNING;

EID: 85028548653     PISSN: 01691864     EISSN: 15685535     Source Type: Journal    
DOI: 10.1080/01691864.2017.1365009     Document Type: Review

References (135)

1. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–444.10.1038/nature14539
2. Jordan MI, Mitchell TM. Machine learning:trends, perspectives, and prospects. Science. 2015;349(6245):255–260.10.1126/science.aaa8415
3. Böhmer W, Springenberg JT, Boedecker J, et al. Autonomous learning of state representations for control:an emerging field aims to autonomously learn state representations for reinforcement learning agents from their real-world sensor observations. KI-Künstliche Intelligenz. 2015;29(4):353–362.10.1007/s13218-015-0356-1
4. Stigler SM. Gauss and the invention of least squares. Ann Stat. 1981;9(3):465–474.10.1214/aos/1176345451
5. Haykin S. Neural networks:a comprehensive foundation. 2nd ed. Upper Saddle River (NJ):Prentice Hall; 2004.
6. Bryson AE, Denham WF, Dreyfus SE. Optimal programming problems with inequality constraints. AIAA J. 1963;1(11):2544–2550.10.2514/3.2107
7. Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1986;323:533–536.10.1038/323533a0
8. Werbos P. Beyond regression:new tools for prediction and analysis in the behavioral sciences [PhD dissertation]. Cambridge (MA):Department Statistics, Harvard University; 1974.
9. Cybenko G. Approximation by superpositions of a sigmoidal function. Math Control Signals Sys. 1989;2(4):303–314.10.1007/BF02551274
10. Hochreiter S. Untersuchungen zu dynamischen neuronalen netzen [master’s thesis]. Institut Fur Informatik, Technische Universitat; Munchen; 1991.
11. Hochreiter S. The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int J Uncertainty Fuzziness Knowledge-Based Syst. 1998;6(2):107–116.
12. Miyamoto H, Kawato M, Setoyama T, et al. Feedback-error-learning neural network for trajectory control of a robotic manipulator. Neural Netw. 1998;1(3):251–265.
13. Lewis FW, Jagannathan S, Yesildirak A. Neural network control of robot manipulators and non-linear systems. Philadelphia (PA):CRC Press; 1989.
14. Miller WT, Werbos PJ, Sutton RS. Neural networks for control. Cambridge (MA):MIT Press; 1995.10.1007/978-3-642-57760-4
15. Lin CT, Lee CSG. Neural-network-based fuzzy logic control and decision system. IEEE Trans Comput. 1991;40(12):1320–1336.10.1109/12.106218
16. Pomerleau DA. ALVINN, an autonomous land vehicle in a neural network (No. AIP-77). Computer Science Department, Carnegie Mellon University; 1989.
17. Oh K, Jung K. GPU implementation of neural networks. Pattern Recognit. 2004;37(6):1311–1314.10.1016/j.patcog.2004.01.013
18. Hinton GE, Osindero S, Teh Y. A fast learning algorithm for deep belief nets. Neural Comput. 2006;18(7):1527–1554.10.1162/neco.2006.18.7.1527
19. Dean J, Corrado G, Monga R, et al. Large scale distributed deep networks. Adv Neural Inf Process Syst. 2012;25:1223–1231.
20. Tani J, Ito M, Sugita Y. Self-organization of distributedly represented multiple behavior schemata in a mirror system:reviews of robot experiments using RNNPB. Neural Netw. 2004;17(8–9):1273–1289.10.1016/j.neunet.2004.05.007
21. Ijspeert AJ. Central pattern generators for locomotion control in animals and robots:a review. Neural Netw. 2008;21(4):642–653.10.1016/j.neunet.2008.03.014
22. Gashler M, Martinez T. Temporal nonlinear dimensionality reduction. In:International Joint Conference on Neural Networks (IJCNN 2011); 2011, Jul 31–Aug 05; San Jose, CA. p. 1959–1966.
23. Pomerleau DA. Neural network perception for mobile robot guidance. Vol. 239. New York (NY):Springer Science & Business Media; 2012.
24. Thrun S. Learning to play the game of chess. Advances in Neural Information Processing System:Proceedings of the 1994 Conference; Denver, CO.
25. Campbell M, Hoane AJ, Hsu F. Deep blue. Artif Intell. 2002;134(1–2):57–83.10.1016/S0004-3702(01)00129-1
26. Pinto N, Cox DD, DiCarlo JJ. Why is real-world visual object recognition hard? PLoS Comput Biol. 2008;4(1):151–156.
27. Schmidhuber J. Deep learning in neural networks:an overview. Neural Netw. 2015;61(1):85–117.10.1016/j.neunet.2014.09.003
28. Graves A, Liwicki M, Fernández S, et al. A novel connectionist system for unconstrained handwriting recognition. Pattern Anal Mach Intell IEEE Trans. 2009;31(5):855–868.
29. Yang M, Ji S, Xu W, et al. Detecting human actions in surveillance videos. TREC Video Retrieval Evaluation Workshop; 2009.
30. Lin M, Chen Q, Yan S. Network in network; 2013. Available from:https://arxiv.org/abs/1312.4400
31. Ciresan D, Giusti A, Gambardella LM, et al. Deep neural networks segment neuronal membranes in electron microscopy images. Adv Neural Inf Process Sys. 2012;25:2843–2851.
32. Roux L, Racoceanu D, Lomenie N, et al. Mitosis detection in breast cancer histological images an ICPR 2012 contest. J Pathol Inform. 2013;4(8).
33. Cireşan DC, Giusti A, Gambardella LM, et al. Mitosis detection in breast cancer histology images with deep neural networks. In:Mori K, Sakuma I, Sato Y, Barillot C, Navab N, editors. Medical Image Computing and Computer-Assisted Intervention–MICCAI. Nagoya:Springer; 2013.
34. Cireşan D, Meier U, Masci J, et al. A committee of neural networks for traffic sign classification. International Joint Conference on Neural Networks (IJCNN); San Jose, CA; 2011. p. 1918–1921.
35. Ciresan D, Meier U, Schmidhuber J. Multi-column deep neural networks for image classification. In:IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Providence, RI; 2012. p. 3642–3649.
36. Dunne RA, Campbell NA. On the pairing of the softmax activation and cross-entropy penalty functions and the derivation of the softmax activation function. In:Proceedings of 8th Australian Conference on the Neural Networks. Vol. 185. Melbourne; 1997. p. 181.
37. Wilson DR, Martinez TR. The general inefficiency of batch training for gradient descent learning. Neural Netw. 2003;16(10):1429–1451.10.1016/S0893-6080(03)00138-2
38. Tieleman T, Hinton G. Rmsprop:divide the gradient by a running average of its recent magnitude. COURSERA:Neural Networks for Machine Learning. Technical report, 2012;31.
39. Kingma D, Ba J. Adam:a method for stochastic optimization; 2014. Available from:https://arxiv.org/abs/1412.6980
40. Vincent P, Larochelle H, Lajoie I, et al. Stacked denoising dutoencoders:learning useful representations in a deep network with a local denoising criterion. J Mach Learning Res. 2010;11:3371–3408.
41. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1097–1105.
42. LeCun Y, Bengio Y. Convolutional networks for images, speech, and time series. In:Arbib M, editor. The handbook of brain theory and neural networks. 2nd ed. Cambridge (MA):MIT Press; 2003. p. 1–14.
43. Werbos PJ. Backpropagation through time:what it does and how to do it. Proc IEEE. 1990;78(10):1550–1560.10.1109/5.58337
44. Sjöberg J, Zhang Q, Ljung L, et al. Nonlinear black-box modeling in system identification:a unified overview. Automatica. 1995;31(12):1691–1724.10.1016/0005-1098(95)00120-8
45. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735–1780.10.1162/neco.1997.9.8.1735
46. Atkeson CG, Santamaria JC. A comparison of direct and model-based reinforcement learning. In:IEEE International Conference on Robotics and Automation. Albuquerque (NM). 1997. p. 3557–3564.
47. Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning. Nature. 2015;518:529–533.10.1038/nature14236
48. LeCun Y, Boser B, Denker JS, et al. Backpropagation applied to handwritten zip code recognition. Neural Comput. 1989;1(4):541–551.10.1162/neco.1989.1.4.541
49. Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278–2324.10.1109/5.726791
50. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition; 2014. Available from:https://arxiv.org/abs/1409.1556
51. Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Boston, MA; 2015. p. 1–9.
52. Chen LC, Papandreou G, Kokkinos I, et al. Semantic image segmentation with deep convolutional nets and fully connected crfs; 2014. Available from:https://arxiv.org/abs/1412.7062
53. Sermanet P, Eigen D, Zhang X, et al. Overfeat:integrated recognition, localization and detection using convolutional networks; 2013. Available from:https://arxiv.org/abs/1312.6229
54. Dong C, Loy CC, He K, et al. Learning a deep convolutional network for image super-resolution. In:European Conference on Computer Vision; Zurich; 2014. p. 184–199.
55. Sun Y, Wang X, Tang X. Deep convolutional network cascade for facial point detection. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Portland, OR; 2013. p. 3476–3483.
56. Taigman Y, Yang m, Ranzato MA, et al. Deepface:closing the gap to human-level performance in face verification. In:Proceedings of the IEEE Conf on Computer Vision and Pattern Recognition; Columbus, OH; 2014. p. 1701–1708.
57. Zhou B, Lapedriza A, Xiao J, et al. Learning deep features for scene recognition using places database. In:Advances in Neural Information Processing System; Montreal; 2014. p. 487–495.
58. Ji S, Xu W, Yang M, et al. 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Analysis Mach Intell. 2013;35(1):221–231.10.1109/TPAMI.2012.59
59. Graves A, Mohamed MR, Hinton G., Speech recognition with deep recurrent neural networks. In:IEEE International Conference on Acoustics, Speech and Signal Proceedings (ICASSP); Vancouver, BC, Canada 2013. p. 6645–6649.
60. Bakshi BR, Stephanopoulos G. Wave-net:a multiresolution, hierarchical neural network with localized learning. AIChE J. 1993;39(1):57–81.10.1002/(ISSN)1547-5905
61. Arel I, Rose DC, Karnowski TP. Deep machine learning–a new frontier in artificial intelligence research [research frontier]. IEEE Comput Intell Mag. 2010;5(4):13–18.10.1109/MCI.2010.938364
62. Kim Y, Moon T. Human detection and activity classification based on micro-doppler signatures using deep convolutional neural networks. IEEE Geosci Remote Sens Lett. 2016;13(1):8–12.10.1109/LGRS.2015.2491329
63. Liu F, Shen C, Lin G, et al. Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans Pattern Anal Mach Intell. 2016;38(10):2024–2039.10.1109/TPAMI.2015.2505283
64. Eitel A, Springenberg JT, Spinello L, et al. Multimodal deep learning for robust rgb-d object recognition. In:2015 IEEE/RSJ International Conference on Intelligent Robots and System (IROS); Hamburg, Germany; 2015 Sep. p. 681–687.
65. Bohannon J. Helping robots see the big picture. Science. 2014;346(6206):186–187.10.1126/science.346.6206.186
66. Sweller J. Evolutionary bases of human cognitive architecture:implications for computing education. In:Proceedings of the Fourth International Workshop on Computing Education Research; Sydney, Australia; 2008. p. 1–2.
67. Doya K. What are the computations of the cerebellum, the basal ganglia and the cerebral cortex? Neural Netw. 1999;12(7–8):961–974.10.1016/S0893-6080(99)00046-5
68. Langley P, Laird JE, Rogers S. Cognitive architectures:research issues and challenges. Cognitive Syst Research. 2009;10(2):141–160.10.1016/j.cogsys.2006.07.004
69. Sun R. Cognition and multi-agent interaction:from cognitive modeling to social simulation. New York (NY):Cambridge University Press; 2006.
70. Duch W, Oentaryo RJ, Pasquier M. Cognitive architectures:where do we go from here? AGI. 2008 Jun;171:122–136.
71. A roadmap for US robotics:from internet to robotics; 2016 ed.
72. World Technology Evaluation Center, Inc. International assessment of research and development in robotics. Baltimore (MD); 2006.
73. FY2009-2034 unmanned systems integrated roadmap. Washington (DC):Department of Defence (US); 2009.
74. Material Handling Institute. Material handling and logistics U.S. roadmap 2.0; 2017.
75. DARPA Robotics Challenge [Internet]. [cited 2017 May 20]. Available from:https://www.darpa.mil/program/darpa-robotics-challenge
76. Punjani AP, Abbeel AP. Deep learning helicopter dynamics models. In:2015 IEEE International Conference on Robotics and Automation (ICRA); Seattle, WA; 2015. p. 3223–3230.
77. Neverova N, Wolf C, Taylor GW, et al. Multi-scale deep learning for gesture detection and localization. In:Computer Vision-ECCV 2014 Workshops; 2014. p. 474–490.
78. Mariolis I, Peleka G, Kargakos A, et al. Pose and category recognition of highly deformable objects using deep learning. In:2015 International Conference on Advanced Robotics (ICAR); Istanbul; 2015. p. 655–662.
79. Yang Y, Li Y, Fermüller C, et al. Robot learning manipulation action plans by watching unconstrained videos from the world wide web. 29th AAAI Conference on Artificial Intelligence (AAAI-15); Austin (TX); 2015.
80. Chen W, Qu T, Zhou Y, et al. Door recognition and deep learning algorithm for visual based robot navigation. In:2014 IEEE International Conference on Robotics and Biomimetics (ROBIO); Bali; 2014. p. 1793–1798.
81. Gao Y, Hendricks LA, Kuchenbecker KJ, et al. Deep learning for tactile understanding from visual and haptic data; 2015. Available from:https://arxiv.org/abs/1511.06065
82. Yu J, Weng K, Liang G, et al. A vision-based robotic grasping system using deep learning for 3D object recognition and pose estimation. 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO); Shenzhen; 2013. p. 1175–1180.
83. Lenz I, Lee H, Saxena A. Deep learning for detecting robotic grasps. Int J Robotics res. 2015;34(4–5):705–724.10.1177/0278364914549607
84. Redmon J, Angelova A. Real-time grasp detection using convolutional neural networks. In:2015 IEEE International Conference on Robotics and Automation (ICRA); Seattle (WA); 2015. p. 1316–1322.
85. Levine S, Pastor P, Krizhevsky A, et al. Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection; 2016. Available from:https://arxiv.org/abs/1603.02199
86. Ouyang W, Wang X. Joint deep learning for pedestrian detection. IEEE International Conference on Computer Vision; Sidney; 2013. p. 2056–2063.
87. Wu J, Yildirim I, Lim JJ, et al. Galileo:perceiving physical object properties by integrating a physics engine with deep learning. Adv Neural Inf Process Syst. 2015;28:127–135.
88. Schmitz A, Bansho Y, Noda K, et al. Tactile object recognition using deep learning and dropout. 14th IEEE-RAS International Conference on Humanoid Robots; Madrid, Spain; 2014. p. 1044–1050.
89. Zheng H, Yang Z, Liu W, et al. Improving deep neural networks using softplus units. In:2015 International Joint Conference on Neural Networks (IJCNN); Anchorage, AL; 2015. p. 1–4.
90. Xu B, Wang N, Chen T, et al. Empirical evaluation of rectified activations in convolutional network. 2015. Available from:https://arxiv.org/abs/1505.00853
91. Gashler MS, Ashmore SC. Modeling time series data with deep Fourier neural networks. Neurocomputing. 2016;188:3–11.10.1016/j.neucom.2015.01.108
92. Zou H, Hastie T. Regularization and variable selection via the elastic net. J Roy Stat Soc:Series B (Stat Methodol). 2005;67(2):301–320.10.1111/rssb.2005.67.issue-2
93. Srivastava N, Hinton GE, Krizhevsky A, et al. Dropout:a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929–1958.
94. Wan L, Zeiler M, Zhang S, et al. Regularization of neural networks using dropconnect. In:Proceedings of the 30th International Conference on Machine Learning (ICML-13); 2013. p. 1058–1066.
95. Rifai S, Vincent P, Muller X, et al. Contractive auto-encoders:explicit invariance during feature extraction. In:Proceedings of the 28th International Conference on Machine Learning (ICML-11); 2011. p. 833–840.
96. Li Z, Fan Y, Liu W. The effect of whitening transformation on pooling operations in convolutional autoencoders. EURASIP J Adv Signal Proc. 2015;2015:1–11.10.1186/s13634-015-0222-1
97. Jarrett K, Kavukcuoglu K, LeCun Y. What is the best multi-stage architecture for object recognition? In:IEEE 12th International Conference on Computer Vision; Kyoto, Japan; 2009. p. 2146–2153.
98. Ioffe S, Szegedy C. Batch normalization:accelerating deep network training by reducing internal covariate shift; 2015. Available from:https://arxiv.org/abs/1502.03167
99. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Seattle, WA; 2016. p. 770–778.
100. Abadi M, Agarwal A, Barham P, et al. Tensorflow:large-scale machine learning on heterogeneous distributed systems; 2016. Available from:https://arxiv.org/abs/1603.04467
101. Bergstra J, Bastien F, Breuleux O, et al. Theano:deep learning on gpus with python. Vol. 3. In:NIPS 2011, BigLearning Workshop; Granada; 2011.
102. Goodfellow J, Warde-Farley D, Lamblin P, et al. Pylearn2:a machine learning research library; 2013. Available from:https://arxiv.org/abs/1308.4214.
103. Chollet F. Keras:deep learning library for theano and tensorflow; 2015. Available from:https://keras.io/k
104. Collobert R, Kavukcuoglu K, Farabet C. Torch7:a matlab-like environment for machine learning. BigLearn, NIPS Workshop (No. EPFL-CONF-192376); Granada, Spain; 2011.
105. Jia Y, Shelhamer E, Donahue J, et al. Caffe:convolutional architecture for fast feature embedding. In:Proceedings of 22nd ACM International Conference on Multimedia; Orlando, FL; 2014. p. 675–678.
106. Attardi G. Deepnl:a deep learning nlp pipeline. In:Proceedings of NAACL-HLT; Denver, CO; 2015. p. 109–115.
107. Gashler M. Waffles:a machine learning toolkit. J Mach Learn Res. 2012 Jul; 2383–2387.
108. Johnson L. Theanets documentation. Available from:https://theanets.readthedocs.org/en/stable/
109. Povey D, Ghoshal A, Boulianne G, et al. The Kaldi speech recognition toolkit. In:IEEE 2011 workshop on automatic speech recognition and understanding (No. EPFL-CONF-192584); Waikoloa (HI):IEEE Signal Processing Society; 2011.
110. Weninger F, Bergmann J, Schuller BW. Introducing CURRENNT:the munich open-source CUDA recurrent neural network toolkit. J Mach Learn Res. 2015;16(3):547–551.
111. Kustikova VD, Druzhkov PN. A survey of deep learning methods and software for image classification and object detection. 9-th Open German-Russian Workshop on PATTERN RECOGNITION and IMAGE UNDERSTANDING; Koblenz, Germany; December 1–5; 2014.
112. Finn C, Tan XY, Duan Y, et al. Deep spatial autoencoders for visuomotor learning; 2015. Available from:https://arxiv.org/abs/1509.06113
113. Watter M, Springenberg J, Boedecker J, et al. Embed to control:a locally linear latent dynamics model for control from raw images. Adv Neural Inf Proc Sys. 2015;28:2746–2754.
114. Noda K, Arie H, Suga Y, et al. Multimodal integration learning of robot behavior using deep neural networks. Rob Auton Sys. 2014;62(6):721–736.10.1016/j.robot.2014.03.003
115. Polydoros AS, Nalpantidis L, Kruger V. Real-time deep learning of robotic manipulator inverse dynamics. In:2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS); 2015. p. 3442–3448.
116. Günther J, Pilarski PM, Helfrich G, et al. Intelligent laser welding through representation, prediction, and control learning:an architecture with deep neural networks and reinforcement learning. Mechatronics. 2015;34:1–11.
117. Günther J, Pilarski PM, Helfrich G, et al. First steps towards an intelligent laser welding architecture using deep neural networks and reinforcement learning. Procedia Technol. 2014;15:474–483.10.1016/j.protcy.2014.09.007
118. Masci J, Meier U, Cireşan D, et al. Stacked convolutional auto-encoders for hierarchical feature extraction. In:Artificial Neural Networks and Machine Learning–ICANN 2011; 2011. p. 52–59.
119. Ashmore SC, Gashler MS. Practical techniques for using neural networks to estimate state from images. In:15th IEEE International Conference on Machine Learning and Applications (ICMLA); Anaheim, CA; 2016. p. 916–919.
120. Rifai S, Vincent P, Muller X, et al. Contractive auto-encoders:explicit invariance during feature extraction. In:Proceedings of the 28th International Conference on Machine Learning (ICML-11); Bellevue, WA; 2011. p. 833–840.
121. Jain A, Koppula HS, Soh S, et al. Brain4Cars:car that knows before you do via sensory-fusion deep learning architecture; 2016. Available from:https://arxiv.org/abs/1601.00740
122. Lenz I, Knepper R, Saxena A. Deepmpc:learning deep latent features for model predictive control. In:Robotics:Science and Systems XI; Rome; 2015.
123. Hwang J, Jung M, Madapana N, et al. Achieving “synergy” in cognitive behavior of humanoids via deep learning of dynamic visuo-motor-attentional coordination. In:IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids); Seoul; 2015. p. 817–824.
124. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735–1780.10.1162/neco.1997.9.8.1735
125. Zhang T, Kahn G, Levine S, et al. Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search; 2015. Available from:https://arxiv.org/abs/1509.06791
126. Lillicrap TP, Hunt JJ, Pritzel A, et al. Continuous control with deep reinforcement learning; 2015. Available from:https://arxiv.org/abs/1509.02971
127. Finn C, Levine S, Abbeel P. Guided cost learning:deep inverse optimal control via policy optimization; 2016. Available from:https://arxiv.org/abs/1603.00448
128. Levine S, Finn C, Darrell T, et al. End-to-end training of deep visuomotor policies. J Mach Learn Res. 2016;17:1–40.
129. Rosenstein M, Barto A. Supervised actor-critic reinforcement learning. In:Si J, Barto AG, Powell WB, et al., editors. Handbook of Learning and Approximate dynamic programming. Wiley; 2004.
130. Houthooft R, Chen X, Duan Y, et al. VIME:variational information maximizing exploration. In:Advances in Neural Information Processing Systems; 2016. p. 1109–1117.
131. Osband I, Blundell C, Pritzel A, et al. Deep exploration via bootstrapped DQN. In:Advances in Neural Information Processing Systems; 2016. p. 4026–4034.
132. Pinto L, Gupta A. Supersizing self-supervision:learning to grasp from 50 k tries and 700 robot hours; 2015. Available from:https://arxiv.org/abs/1509.06825
133. Kappler D, Bohg J, Schaal S. Leveraging big data for grasp planning. 2015 IEEE International Conference on Robotics and Automation (ICRA); Seattle (WA); 2015. p. 4304–4311.
134. Pratt GA. Is a cambrian explosion coming for robotics? J Econ Perspect. 2015;29(3):51–60.10.1257/jep.29.3.51
135. Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks; 2013. Available from:https://arxiv.org/abs/1312.6199