http://robotics.caltech.edu/wiki/api.php?action=feedcontributions&user=Dpastorm&feedformat=atomRobotics - User contributions [en]2024-03-29T05:17:11ZUser contributionsMediaWiki 1.26.0http://robotics.caltech.edu/wiki/index.php?title=People&diff=1641People2019-05-25T06:24:41Z<p>Dpastorm: </p>
<hr />
<div>__NOTOC__<br />
<br />
{| width=100% border=1 cellpadding=2 cellspacing=2<br />
|- valign=top<br />
|<br />
The people currently affiliated with the Burdick research group:<br />
<br />
=== Faculty and Staff === <br />
* [[JoelBurdick | Prof. Joel Burdick]]<br />
* Sonya Lincoln (the administative asst. for Prof.s Burdick, Blanquart, Hunt)<br />
<br />
=== Visiting Associates === <br />
* Prof. Elon Rimon (Technion, Israel Institute of Technology) <br />
<br />
=== Post-Doctoral Students === <br />
* Kun Li <br />
* [http://www.its.caltech.edu/~ysui/ Yanan Sui] <br />
|<br />
=== Graduate Students === <br />
* Amanda Bouman<br />
* Joseph Bowkett<br />
* Matt Burkhardt<br />
* Richard Cheng<br />
* Sumanth Dathathri<br />
* Jeffrey A Edlund <br />
* Ellen Feldman <br />
* Daniel Naftalovich<br />
* Daniel Pastor Moreno<br />
* [http://robotics.caltech.edu/~melissa Melissa Tanner] <br />
* Luke Urban<br />
<br />
=== Visiting Grad Students === <br />
* Hiroki Nagashima<br />
|}<br />
<br />
== Former Group Members == <br />
<br />
{| width=100% border=1 cellpadding=2 cellspacing=2<br />
|- valign=top<br />
| rowspan=2 |<br />
=== Former Graduate Students === <br />
* Pablo Abad-Manterola (Exponent) <br />
* Tom Allen (Pneubotics) <br />
* Eddie Branchaud (Teach for America, NY) <br />
* Lance Cai (Boeing Control Group) <br />
* Shiyan Cao (CitiBank) <br />
* Bedri Cetin <br />
* I-Ming Chen (Nanyang Technological University) <br />
* Greg Chirikjian (Johns Hopkins University) <br />
* Howie Choset (Carnegie Mellon University) <br />
* Tim Chung (Naval Post-Graduate School) <br />
* Tom Desautels (Univ. College London) <br />
* Noel duToit(Naval Post-graduate School) <br />
* [http://www.kjerstin.com Kjerstin Easton] (Apple) <br />
* Andy Fong (McKinsey) <br />
* [http://robotics.caltech.edu/~ebraheem Ebraheem Fontaine] (Fair Isaac Corp.) <br />
* Tim Frank<br />
* Bill Goodwine (Univ. of Notre Dame) <br />
* Paul Hebert (Apple) <br />
* Matanya Horowitz (founder, Cognitive Robotics Corp.)<br />
* Nick Hudson (Google) <br />
* Hao Jiang <br />
* Kristo Kriechbaum (Technical Staff, NASA/JPL) <br />
* Sharon Laubach (Technical Staff, NASA/JPL) <br />
* Yongqiang Liang (Intel Corp.) <br />
* Qiao Lin (Columbia University) <br />
* Zhao Liu (Apple)<br />
* Mark Long (Amazon)<br />
* Jeremy Ma (Apple) <br />
* Richard Mason (RAND Corporation) <br />
* Todd Murphey (Northwestern) <br />
* Jim Ostrowski (Blue River Robotics) <br />
* Sam Pfister (Checchi Capitol) <br />
* Ann Marie Polsenberg-Thomas (St. Thomas University) <br />
* Jim Radford (InDigita Corp.) <br />
* Krishna Shankar (Google)<br />
* Rangoli Sharan (Humin, Inc.)<br />
* Andrew Brett Slatkin (Exponent Corporation) <br />
* Patricio Vela (Georgia Tech.) <br />
* Michael Wolf (Technical Staff, JPL)<br />
|<br />
<br />
=== Former Postdocs === <br />
* Rachel Berquist (Scripps Oceanographic Institute) <br />
* Jorge Cham ([http://www.phdcomics.com/ professional cartoonist]) <br />
* SangHyun Chang (Electronics Research Labs, Samsung) <br />
* Malcolm MacIver (BioEngineering, Northwestern University) <br />
* Kristi Morgensen--joint with Prof. Richard Murray (Univ. of Washington, Aero Dept.) <br />
* Zoran Nenadic (BioMedical Engineering, U.C. Irvine) <br />
* Elon Rimon (Mechanical Engineering, Technion, Israel Institute of Technology) <br />
* Stergios Roumeliotis (C.S. Department, Univ. of Minnesota) <br />
* Prof. B. Shashikanth--joint with J. Marsden and R. Murray (New Mexico State Univ.) <br />
* Sota Shimizu (Waseda University, Tokyo, Japan) <br />
* Michael Shusser (Thermofluids research group, Rafael, Israel) <br />
* Hiroaki Yamaguchi <br />
* Dr. Milos Zefran (Univ. of Illinois, Chicago)<br />
<br />
|- valign=top cellpadding=2<br />
|<br />
<br />
=== Former Visiting Associates === <br />
* [http://robotics.caltech.edu/~atsushi Dr. Atsushi Yamashita] (Shizuoka University, Japan) <br />
* Prof. Hisashi Date (National Defense Academy of Japan) <br />
* [http://robotics.caltech.edu/~kajita/kajita.html Dr. Shuuji Kajita] (Mechanical Engineering Lab., MITI, Japan) <br />
* Dr. Naoki Mitsumoto (Denso Corporation, Japan) <br />
* Jean Ponce (Ecole Normal Superiore, Paris, France) <br />
* Nobuaki Takanashi (NEC Corporation) <br />
|}</div>Dpastormhttp://robotics.caltech.edu/wiki/index.php?title=File:SparseMPC.pdf&diff=1331File:SparseMPC.pdf2018-02-05T21:31:17Z<p>Dpastorm: </p>
<hr />
<div></div>Dpastormhttp://robotics.caltech.edu/wiki/index.php?title=GP_SSM&diff=1330GP SSM2018-02-05T21:30:38Z<p>Dpastorm: /* Papers which are more oriented toward control */</p>
<hr />
<div>This page gathers references and materials related to the study of <br />
* Gaussian Process (GP) State Space Models (SSM)<br />
* Deep Learning<br />
* Koopman Spectral Methods.<br />
<br />
== Gaussian Process Approaches ==<br />
<br />
=== Basic Gaussian Process Info ===<br />
* Rasmussen and Williams<br />
<br />
=== Web Links ===<br />
* [http://dsc.ijs.si/jus.kocijan/GPdyn/ Bibliography on GP Models in Dynamical Systems]<br />
<br />
=== Papers on GP-SSMs ===<br />
* J.M. Wang, D.J. Fleet, A. Hertzmann, [[Media:GPDynamicModels.pdf | Gaussian Process Dynamical Models]]<br />
* R. Turner, M.P. Deisenroth, C.E. Rasmussen, [[Media:StateSpaceInferenceLearningGPs.pdf | State-Space Inference and Learning with Gaussian Process]];<br />
* A. McHutchon, [[Media:NonlinearModellingControlUsingGPs.pdf | Nonlinear Modelling and Control Using Gaussian Processes]] (Ph.D. thesis, Cambridge University)<br />
* J. Ko, D. Fox, [[Media:GPBayesFilters.pdf | GP-BayesFilters: Bayesian filtering using Gaussian Process Prediction and Observation Models]]<br />
* F. Perez-Cruz, S.V. Vaerenbergh, J.J. Murrillo-Fuentes, M. Lazarro-Gredilla, and I. Santamaria, [[Media:GPforNonlinearSignalProcessing.pdf | Gaussian Processes for Nonlinear Signal Processing]];<br />
* A. Svensson, A. Solin, S. Sarkka, T.B. Schon, [[Media:EfficientBayesianLearmingGPSSMs.pdf | Computationall Efficient Bayesian Learning of Gaussian Process State Space Models]]<br />
* A.C. Damianou, M.K. Titsias, N.D. Lawrence, [[Media:VariationalGPDynSystems.pdf | Variational Gaussian Process Dynamical Systems]]<br />
* M.P. Deisenroth, D. Fox, C.E. Rasmussen, [[Media:GPsDataEfficientLearning.pdf | Gaussian Processes for Data-Efficient Learning in Robotics and Control]];<br />
* K. Jocikan, [[Media:DynamicGPModelsOverview.pdf | Dynamic GP Models: An Overview and Recent Developments]];<br />
* A. Solin, S. Sarkka, [[Media:ReducedRankGPR.pdf | Hilbert Space Methods for Reduced-Rank Gaussian Process Regression]]; (ArXiv.1401.5508)<br />
* C.L.C. Mattos, Z. Dai, A. Damianou, J. Forth, G.A. Barreto, N. Lawrence, [[Media:RecurrentGaussianProcesses.pdf | Recorruent Gaussian Processes]]<br />
* N.D. Lawrence, A.J. Moore, [[Media:HierarchicalGPLatentVariableModels.pdf | Hierarchical Gaussian Process Latent Variable Models]]<br />
* M.K. Titsias, N.D. Lawrence, [[Media:BayesianGPLatentVariableModel.pdf | Bayesian Gaussian Process Latent Variable Model]]<br />
* R. Calandra, J. Peters, C.E. Rasmussen, M.P. Deisenroth, [[Media:ManifoldGPR.pdf | Manifold Gaussian Processes for Regression]]<br />
* F. Berkenkamp and A.P. Schoellig, [[Media:SafeRobustLearningControlwithGPs.pdf | Safe and Robust Learning Control with Gaussian Processes]]<br />
* E.B. Fox, E.B. Sudderth, M.I. Jordan, A.S. Willsky, [[Media:SharingFeaturesDynamicalSystems.pdf | Sharing Features Among Dynamical Systems with Beta Processes]]<br />
* J.M. Wang, D.j. Fleet, A. Hertzmann, [[Media:GPDynamicalModelsHumanMotion.pdf | Gaussian Process Dynamical Models for Human Motion]]<br />
* E.D. Klenske, P. Hennig, [[Media:DualControlApproxBayesianRL.pdf | Dual Control for Approximate Bayesian Reinforcement Learning]]<br />
* Y. Pan and E.A. Theodorou, [[Media:DataDrivenDDPUsingGPs.pdf | Data-Driven Differential Dynamic Programming Using Gaussian Processes]]<br />
* F. Berkenkamp, R. Moriconi, A.P. Schoellig, A. Krause, [[Media:SafeLearningRegionsAttractionWithGPs.pdf | Safe Learning of Regions of Attraction for Uncertain, Nonlinear Systems with Gaussian Processes]]<br />
* M.P. Deisenroth, J. Peters, C.E. Rasmussen, [[Media:ApproximateDPwithGaussianProcesses.pdf | Approximate Dynamic Programming with Gaussian Processes]]<br />
* R. Frigola, F. Lindsten, T.B. Schon, C.E. Rasmussen, [[Media:IdentificationGPSSMwithParticalEM.pdf | Identification of Gaussian Process State-Space Models with Particle Stochastic Approximation EM]]<br />
<hr /><br />
* Z.Y. Wan and T.P. Sapsis, [[Media:ReducedSpaceGPR.pdf | Reduced-Space Gaussian Process Regression for Data-Driven Forecast of Chaotic Dynamical Systems]], ''arXiv:1611.01583''<br />
* T. Beckers, J. Umlauft, and S. Hirsche, [[Media:ModelBasedGPRControl.pdf | Stable Model-Based Control with Gaussian Process Regression for Robot Manipulators]],<br />
* A. Marco, P. Hennig, S. Schaal, S. Trimpe, [[Media:DesignLQRKernels.pdf | On the Design of LQR Kernels for Efficient Controller Learning]], ''arXiv:1709.07089v1''<br />
* N. Gorbach, S. Bauer, J. Buhmann, [[Media:ScalableVariationalInference.pdf | Scalable Variational Inference for Dynamical Systems]], NIPS 2017, Long Beach, CA, 2017.<br />
* J. Umlauft, T. Beckers, M. Kimmel, S. Hirsche, [[Media:FeedbackLinearlizatingUsingGPs.pdf | Feedback Linearization Using Gaussian Processes]]<br />
* F. Lindsten, M.I. Jordan, T.B. Schon, [[Media:ParticleGibbsWithAncestorSamping.pdf | Particles Gibbs with Ancestor Sampling]], ''J. Machine Learning Research'', vo. 15, pp. 2145-2184.<br />
<br />
== Deep Learning ==<br />
<br />
=== Papers on Deep Learning ''Theory'' ===<br />
* This is the paper that we seek to understand in this reading group.<br />
** A. Achille and S. Soatto, [[Media:InvarianceDisentanglement.pdf | Emergence of Invariance and Disentanglement in Deep Representations]], ''arXiV:1706.01350v2'', Oct. 2017.<br />
* Here are some background papers (i.e., links to many of the references in the Achille and Soatto paper)<br />
** A. Achille and S. Soatto [https://arxiv.org/pdf/1611.01353.pdf Information Dropout: Learning Optimal Representations Through Noisy Computation]<br />
** A. Alemi, I. Fischer, K. Dillon, and K. Murphey, [https://arxiv.org/abs/1612.00410 Deep Variational Information Bottleneck], ''arXiV:1612.00410''<br />
** F. Anselmi, L. Rosasco, T. Poggio, [https://arxiv.org/pdf/1503.05938.pdf On Invariance and Selectivity in Representation Learning]<br />
** Y. Bengio [https://www.iro.umontreal.ca/~lisa/pointeurs/TR1312.pdf Learning Deep Architectures for AI], 2009.<br />
** J. Bruna and S. Mallat, [http://www.cmap.polytechnique.fr/scattering/scattering_cvpr2011.pdf Classification with Scattering Operators], ''CVPR'', 2011.<br />
** P. Chaudhari, A. Choromanska, S. Soatto, Y. LeCun, C. Baldassi, C. Borgs, J. Chayes, L. Sagun, R. Zecchina [https://arxiv.org/abs/1611.01838 Entropy-SGD: Biasing Gradient Descent into Wide Valleys], ''Proceedings of the International Conference on Learning Representations (ICLR)'', 2017.<br />
** N. Tishby and N. Zaslavsky, [[Media:DeepLearningBottleneck.pdf | Deep Learning and the Information Bottleneck Principle]], ''arXiv:1503.02406'', March, 2015.<br />
** D.-A. Clevert, T. Unterthiner, and S. Hochreiter, [https://arxiv.org/abs/1511.07289 Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)], ''arXiv:1511.07289''.<br />
** L. Dinh, R. Pascanu, S. Bengio, Y. Bengio [https://arxiv.org/abs/1703.04933 Sharp Minima Can Generalize For Deep Nets], ''arXiv:1703.04933''<br />
<br />
* P. Chauderi, A.Oberman, S. Osher, S. Soatto, G. Ccarlier, [[Media:DeepNetPDEs.pdf | Deep Relaxation: Partial Differential Equations for Optimizing Deep Neural Networks]], ''arXiV:1704.04932v2''<br />
<br />
==== Review-like papers ====<br />
* J. Schmidhuber, [https://arxiv.org/pdf/1404.7828.pdf Deep Learning in Neural Networks: An Overview], ''arXiV:404.7828v4'', Oct. 2014.<br />
* S. Mallat, [[Media:UnderstandingDeepCNNs.pdf | Understanding Deep Convolutional Networks]], ''Phil. Trans. Royal Society, A, vol. 374, May 15, 2017.<br />
* M.D. Zeiler and R. Fergus, [https://arxiv.org/abs/1311.2901 Visualizing and Understanding Deep Convolutional Networks]<br />
<br />
==== Papers on Scattering Networks ====<br />
''Scattering Networks'' are proposed by Stephan Mallat (of wavelet fame) to understand why deep nets work so well.<br />
* S. Mallat [[Media:GroupInvariantScattering.pdf | Group Invariant Scattering]], 2012.<br />
* J. Anden, S. Mallat, [[Media:DeepScatteringSpectrum.pdf | Deep Scattering Spectrum]], 2015.<br />
* J. Bruna, S. Mallat, [[Media:InvariantScatteringCNNs.pdf | Invariant Scattering Convolution Networks]]<br />
<br />
==== Classics ====<br />
* K. Hornik, M. Stinchcombe, H. White, [[Media:HSH.pdf | Universal Approximation of an Unknown Mapping and Its Derivatives Using Multi-Layer Feedforward Networks]], ''Neural networks'', vol. 3, 1990.<br />
<br />
=== Web Links ===<br />
* [http://deeplearning.net Deeplearning.net]; [http://deeplearningbook.org/ On-line Deep Learning TextBook]<br />
<br />
== Koopman Spectral Method ==<br />
<br />
=== Papers on Koopman Spectral methods ===<br />
* S. Brunton, J. Proctor, N. Kutz, [[Media:DiscoveringEquationsFromData.pdf | Discovering Governing Equations from Data: Sparse Identification of Nonlinear Dyanmical Systems]], ''arXiv:1509.03580v1'' (also, [[Media:BPK_PNAS.pdf | PNAS Version of the paper]]).<br />
* S. L. Brunton, B.W.Brunton, J.L. Proctor, J.N. Kutz, [[Media:KoopmanInvariantSubspaces.pdf | Koopman Invariant Subspaces and Finite Linear Representations of Nonlinear Dynamical Systems for Control]], ''PLOS One'', vol. 11, no. 2, 2016.<br />
* M. Budisic, R. Mohr, I. Mezic, [[Media:AppliedKoopmanism.pdf | Applied Koopmanism]], ''Chaos'', vol. 22, 2012.<br />
* M.O. Williams, C.W. Rowley, I. G. Kevrekidis, [[Media:KernalBasedMethod.pdf | A Kernel-Based Method for Data-Driven Koopman Spectral Analysis]], ''arXiv:1411.2260v4''<br />
* J.L. Proctor, S.L. Brunton, J.N. Kutz, [[Media:DMDwithControl.pdf | Dynamic Mode Decomposition with Control]], SIAM J. Applied Dynamical Systems, vol. 15, no. 1, pp. 142-161, 2016.<br />
* I. Mezic, [[Media:ApplicationsSpectralTheoryKoopman.pdf | On the Applications of the Theory of the Koopman Operator in Dynamical Systems and Control Theory]], ''Proc. IEEE Conf. Decision Control'', 2015<br />
* M.O. Williams, C. Rowley, I.G. Kevrekidis, [[Media:DataDrivenApproximation.pdf | A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition]], ''J. Nonlinear Science'', vol. 25, 2015.<br />
* D. Giannakis, [[Media:DataDrivenSpectralDecomposition.pdf | Data-Driven Spectral Decomposition and Forecasting of ergodic dynamical systems]], ''arXiv:1507.02338v2''<br />
* I. Mezic and A. Surana, [[Media:PeriodicKoopmanModeDecomposition.pdf | Koopman Mode Decomposition for Periodic/Quasi-Periodic Time Dependence]], ''IFAC Papers Online, 48-18, pp. 690697, 2016.<br />
* H. Schaeffer, [[Media:LearningPDEs.pdf | Learning Partial Differential Equations via Data Discovery and Sparse Optimization]], ''J. Royal Society, Proceedings A'', 2017<br />
* J.N. Kutz, X. Fu, S.L. Brunton, [[Media:MultiresolutionDMD.pdf | Multi-resolution Dynamic Mode Decomposition]], ''arXiv:1506.00564''<br />
<br />
==== Papers which are more oriented toward control ====<br />
* D. Goswami and D.A. Paley, [[Media:GlobalBilinearization.pdf | Global Bilinearization and Controllability of Control-Affine Nonlinear Systems: A Koopman Spectral Approach]],<br />
* A. Surana, [[Media:KoopmanObserverBasedSynthesis.pdf | Koopman Based Operator Synthesis for Control-Affine Noninear Systems]], ''Proc. IEEE Conf. Decision and Control'', 2016<br />
* A. Surana and A. Banaszuk, [[Media:LinearObserverSynthesis.pdf | Linear Observer Synthesis for Nonlinear Systems Using Koopman Operator Framework]], ''IFAC Papers Online'', 49-18, pp. 716-723, 2016.<br />
* E. Kaiser, N. Kutz, and S. Brunton, [[Media: sparseMPC.pdf | Sparse identification of nonlinear dynamics for model predictive control in the low-data limit]] ''arXiv preprint'' arXiv:1711.05501 (2017).<br />
<br />
==== Papers which are more oriented toward fluids ====<br />
* I. Mezic, [[Media:AnalysisFluidFlows.pdf | Analysis of Fluid Flows via Spectral Properties of the Koopman Operator]], ''Annual Review of Fluids,'' vol. 45, 357-378, 2013.<br />
* C.W. Rowley and S.T.M. Dawson, [[Media:FlowModelReductionReview.pdf | Model Reduction for Flow Analysis and Control]], ''Annual Review Fluids'', 49:387-417, 2017.<br />
* M.S Hemati, C.W. Rowley, E.A. Deem, L.N. Cattafesta, [[Media:DebiasingDMD.pdf | De-biasing the Dynamic Mode Decomposition for applied Koopman spectral analysis of noisy data sets]], ''arXiv:1502.03854v2''<br />
* J.H. Tu, [[Media:DMDApplicationsTheory.pdf | Dynamic Mode Decomposition, Theory and Applications]], Ph.D. Thesis, Princeton, 2013.<br />
* S Bagheri, [[Media:ShearFlowsThesis.pdf | Analysis and Control of Transitional Shear Flows Using Global Modes]], Ph.D. Thesis, Royal Inst. Technology, Sweden, 2010.<br />
<br />
==== Some Early Papers ====<br />
* Koopman's original paper: [[Media:KoopmanPNAS.pdf | Dynamical Systems of Continuous Spectra]], ''PNAS'' , vol. 18, 1932.<br />
* J. Ding, [[Media:PointSpectrum.pdf | The Point Spectrum of Frobenius-Perron and Koopman Operators]], ''Proc. AMS,'' vol. 126, no. 5, 1998.<br />
* I. Mezic and A. Banaszuk, [[Media:ComparisonSystems.pdf | Comparison of Systems with Complex Behavior]], ''Physica D'', vol. 197, pp. 101-133, 2004.<br />
* Y. Lan and I. Mezic, [[Media:LinearizationInTheLarge.pdf | Linearization in the Large of Nonlinear Systems and Koopman Operator Spectrum]], ''Physica D'', 2013<br />
<br />
==== Other Papers ====<br />
* E.Berger, M. Sastuba, D. Vogt, B. Jung, H.B. Amor, [[Media:EstimationRobotPerturbations.pdf | Estimation of Perturbations in Robotic Behavior using Dynamic Mode Decomposition]], ''Advanced Robotics,'' vol. 25, no. 5, 2015.<br />
* S. Wang, Z. Qiao, [[Media:NuclearNormDMD.pdf | Nuclear Norm Regularized Dynamic Mode Decomposition]], ''IET Signal Processing'', 2016.</div>Dpastormhttp://robotics.caltech.edu/wiki/index.php?title=GP_SSM&diff=1329GP SSM2018-02-05T21:29:38Z<p>Dpastorm: /* Papers which are more oriented toward control */</p>
<hr />
<div>This page gathers references and materials related to the study of <br />
* Gaussian Process (GP) State Space Models (SSM)<br />
* Deep Learning<br />
* Koopman Spectral Methods.<br />
<br />
== Gaussian Process Approaches ==<br />
<br />
=== Basic Gaussian Process Info ===<br />
* Rasmussen and Williams<br />
<br />
=== Web Links ===<br />
* [http://dsc.ijs.si/jus.kocijan/GPdyn/ Bibliography on GP Models in Dynamical Systems]<br />
<br />
=== Papers on GP-SSMs ===<br />
* J.M. Wang, D.J. Fleet, A. Hertzmann, [[Media:GPDynamicModels.pdf | Gaussian Process Dynamical Models]]<br />
* R. Turner, M.P. Deisenroth, C.E. Rasmussen, [[Media:StateSpaceInferenceLearningGPs.pdf | State-Space Inference and Learning with Gaussian Process]];<br />
* A. McHutchon, [[Media:NonlinearModellingControlUsingGPs.pdf | Nonlinear Modelling and Control Using Gaussian Processes]] (Ph.D. thesis, Cambridge University)<br />
* J. Ko, D. Fox, [[Media:GPBayesFilters.pdf | GP-BayesFilters: Bayesian filtering using Gaussian Process Prediction and Observation Models]]<br />
* F. Perez-Cruz, S.V. Vaerenbergh, J.J. Murrillo-Fuentes, M. Lazarro-Gredilla, and I. Santamaria, [[Media:GPforNonlinearSignalProcessing.pdf | Gaussian Processes for Nonlinear Signal Processing]];<br />
* A. Svensson, A. Solin, S. Sarkka, T.B. Schon, [[Media:EfficientBayesianLearmingGPSSMs.pdf | Computationall Efficient Bayesian Learning of Gaussian Process State Space Models]]<br />
* A.C. Damianou, M.K. Titsias, N.D. Lawrence, [[Media:VariationalGPDynSystems.pdf | Variational Gaussian Process Dynamical Systems]]<br />
* M.P. Deisenroth, D. Fox, C.E. Rasmussen, [[Media:GPsDataEfficientLearning.pdf | Gaussian Processes for Data-Efficient Learning in Robotics and Control]];<br />
* K. Jocikan, [[Media:DynamicGPModelsOverview.pdf | Dynamic GP Models: An Overview and Recent Developments]];<br />
* A. Solin, S. Sarkka, [[Media:ReducedRankGPR.pdf | Hilbert Space Methods for Reduced-Rank Gaussian Process Regression]]; (ArXiv.1401.5508)<br />
* C.L.C. Mattos, Z. Dai, A. Damianou, J. Forth, G.A. Barreto, N. Lawrence, [[Media:RecurrentGaussianProcesses.pdf | Recorruent Gaussian Processes]]<br />
* N.D. Lawrence, A.J. Moore, [[Media:HierarchicalGPLatentVariableModels.pdf | Hierarchical Gaussian Process Latent Variable Models]]<br />
* M.K. Titsias, N.D. Lawrence, [[Media:BayesianGPLatentVariableModel.pdf | Bayesian Gaussian Process Latent Variable Model]]<br />
* R. Calandra, J. Peters, C.E. Rasmussen, M.P. Deisenroth, [[Media:ManifoldGPR.pdf | Manifold Gaussian Processes for Regression]]<br />
* F. Berkenkamp and A.P. Schoellig, [[Media:SafeRobustLearningControlwithGPs.pdf | Safe and Robust Learning Control with Gaussian Processes]]<br />
* E.B. Fox, E.B. Sudderth, M.I. Jordan, A.S. Willsky, [[Media:SharingFeaturesDynamicalSystems.pdf | Sharing Features Among Dynamical Systems with Beta Processes]]<br />
* J.M. Wang, D.j. Fleet, A. Hertzmann, [[Media:GPDynamicalModelsHumanMotion.pdf | Gaussian Process Dynamical Models for Human Motion]]<br />
* E.D. Klenske, P. Hennig, [[Media:DualControlApproxBayesianRL.pdf | Dual Control for Approximate Bayesian Reinforcement Learning]]<br />
* Y. Pan and E.A. Theodorou, [[Media:DataDrivenDDPUsingGPs.pdf | Data-Driven Differential Dynamic Programming Using Gaussian Processes]]<br />
* F. Berkenkamp, R. Moriconi, A.P. Schoellig, A. Krause, [[Media:SafeLearningRegionsAttractionWithGPs.pdf | Safe Learning of Regions of Attraction for Uncertain, Nonlinear Systems with Gaussian Processes]]<br />
* M.P. Deisenroth, J. Peters, C.E. Rasmussen, [[Media:ApproximateDPwithGaussianProcesses.pdf | Approximate Dynamic Programming with Gaussian Processes]]<br />
* R. Frigola, F. Lindsten, T.B. Schon, C.E. Rasmussen, [[Media:IdentificationGPSSMwithParticalEM.pdf | Identification of Gaussian Process State-Space Models with Particle Stochastic Approximation EM]]<br />
<hr /><br />
* Z.Y. Wan and T.P. Sapsis, [[Media:ReducedSpaceGPR.pdf | Reduced-Space Gaussian Process Regression for Data-Driven Forecast of Chaotic Dynamical Systems]], ''arXiv:1611.01583''<br />
* T. Beckers, J. Umlauft, and S. Hirsche, [[Media:ModelBasedGPRControl.pdf | Stable Model-Based Control with Gaussian Process Regression for Robot Manipulators]],<br />
* A. Marco, P. Hennig, S. Schaal, S. Trimpe, [[Media:DesignLQRKernels.pdf | On the Design of LQR Kernels for Efficient Controller Learning]], ''arXiv:1709.07089v1''<br />
* N. Gorbach, S. Bauer, J. Buhmann, [[Media:ScalableVariationalInference.pdf | Scalable Variational Inference for Dynamical Systems]], NIPS 2017, Long Beach, CA, 2017.<br />
* J. Umlauft, T. Beckers, M. Kimmel, S. Hirsche, [[Media:FeedbackLinearlizatingUsingGPs.pdf | Feedback Linearization Using Gaussian Processes]]<br />
* F. Lindsten, M.I. Jordan, T.B. Schon, [[Media:ParticleGibbsWithAncestorSamping.pdf | Particles Gibbs with Ancestor Sampling]], ''J. Machine Learning Research'', vo. 15, pp. 2145-2184.<br />
<br />
== Deep Learning ==<br />
<br />
=== Papers on Deep Learning ''Theory'' ===<br />
* This is the paper that we seek to understand in this reading group.<br />
** A. Achille and S. Soatto, [[Media:InvarianceDisentanglement.pdf | Emergence of Invariance and Disentanglement in Deep Representations]], ''arXiV:1706.01350v2'', Oct. 2017.<br />
* Here are some background papers (i.e., links to many of the references in the Achille and Soatto paper)<br />
** A. Achille and S. Soatto [https://arxiv.org/pdf/1611.01353.pdf Information Dropout: Learning Optimal Representations Through Noisy Computation]<br />
** A. Alemi, I. Fischer, K. Dillon, and K. Murphey, [https://arxiv.org/abs/1612.00410 Deep Variational Information Bottleneck], ''arXiV:1612.00410''<br />
** F. Anselmi, L. Rosasco, T. Poggio, [https://arxiv.org/pdf/1503.05938.pdf On Invariance and Selectivity in Representation Learning]<br />
** Y. Bengio [https://www.iro.umontreal.ca/~lisa/pointeurs/TR1312.pdf Learning Deep Architectures for AI], 2009.<br />
** J. Bruna and S. Mallat, [http://www.cmap.polytechnique.fr/scattering/scattering_cvpr2011.pdf Classification with Scattering Operators], ''CVPR'', 2011.<br />
** P. Chaudhari, A. Choromanska, S. Soatto, Y. LeCun, C. Baldassi, C. Borgs, J. Chayes, L. Sagun, R. Zecchina [https://arxiv.org/abs/1611.01838 Entropy-SGD: Biasing Gradient Descent into Wide Valleys], ''Proceedings of the International Conference on Learning Representations (ICLR)'', 2017.<br />
** N. Tishby and N. Zaslavsky, [[Media:DeepLearningBottleneck.pdf | Deep Learning and the Information Bottleneck Principle]], ''arXiv:1503.02406'', March, 2015.<br />
** D.-A. Clevert, T. Unterthiner, and S. Hochreiter, [https://arxiv.org/abs/1511.07289 Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)], ''arXiv:1511.07289''.<br />
** L. Dinh, R. Pascanu, S. Bengio, Y. Bengio [https://arxiv.org/abs/1703.04933 Sharp Minima Can Generalize For Deep Nets], ''arXiv:1703.04933''<br />
<br />
* P. Chauderi, A.Oberman, S. Osher, S. Soatto, G. Ccarlier, [[Media:DeepNetPDEs.pdf | Deep Relaxation: Partial Differential Equations for Optimizing Deep Neural Networks]], ''arXiV:1704.04932v2''<br />
<br />
==== Review-like papers ====<br />
* J. Schmidhuber, [https://arxiv.org/pdf/1404.7828.pdf Deep Learning in Neural Networks: An Overview], ''arXiV:404.7828v4'', Oct. 2014.<br />
* S. Mallat, [[Media:UnderstandingDeepCNNs.pdf | Understanding Deep Convolutional Networks]], ''Phil. Trans. Royal Society, A, vol. 374, May 15, 2017.<br />
* M.D. Zeiler and R. Fergus, [https://arxiv.org/abs/1311.2901 Visualizing and Understanding Deep Convolutional Networks]<br />
<br />
==== Papers on Scattering Networks ====<br />
''Scattering Networks'' are proposed by Stephan Mallat (of wavelet fame) to understand why deep nets work so well.<br />
* S. Mallat [[Media:GroupInvariantScattering.pdf | Group Invariant Scattering]], 2012.<br />
* J. Anden, S. Mallat, [[Media:DeepScatteringSpectrum.pdf | Deep Scattering Spectrum]], 2015.<br />
* J. Bruna, S. Mallat, [[Media:InvariantScatteringCNNs.pdf | Invariant Scattering Convolution Networks]]<br />
<br />
==== Classics ====<br />
* K. Hornik, M. Stinchcombe, H. White, [[Media:HSH.pdf | Universal Approximation of an Unknown Mapping and Its Derivatives Using Multi-Layer Feedforward Networks]], ''Neural networks'', vol. 3, 1990.<br />
<br />
=== Web Links ===<br />
* [http://deeplearning.net Deeplearning.net]; [http://deeplearningbook.org/ On-line Deep Learning TextBook]<br />
<br />
== Koopman Spectral Method ==<br />
<br />
=== Papers on Koopman Spectral methods ===<br />
* S. Brunton, J. Proctor, N. Kutz, [[Media:DiscoveringEquationsFromData.pdf | Discovering Governing Equations from Data: Sparse Identification of Nonlinear Dyanmical Systems]], ''arXiv:1509.03580v1'' (also, [[Media:BPK_PNAS.pdf | PNAS Version of the paper]]).<br />
* S. L. Brunton, B.W.Brunton, J.L. Proctor, J.N. Kutz, [[Media:KoopmanInvariantSubspaces.pdf | Koopman Invariant Subspaces and Finite Linear Representations of Nonlinear Dynamical Systems for Control]], ''PLOS One'', vol. 11, no. 2, 2016.<br />
* M. Budisic, R. Mohr, I. Mezic, [[Media:AppliedKoopmanism.pdf | Applied Koopmanism]], ''Chaos'', vol. 22, 2012.<br />
* M.O. Williams, C.W. Rowley, I. G. Kevrekidis, [[Media:KernalBasedMethod.pdf | A Kernel-Based Method for Data-Driven Koopman Spectral Analysis]], ''arXiv:1411.2260v4''<br />
* J.L. Proctor, S.L. Brunton, J.N. Kutz, [[Media:DMDwithControl.pdf | Dynamic Mode Decomposition with Control]], SIAM J. Applied Dynamical Systems, vol. 15, no. 1, pp. 142-161, 2016.<br />
* I. Mezic, [[Media:ApplicationsSpectralTheoryKoopman.pdf | On the Applications of the Theory of the Koopman Operator in Dynamical Systems and Control Theory]], ''Proc. IEEE Conf. Decision Control'', 2015<br />
* M.O. Williams, C. Rowley, I.G. Kevrekidis, [[Media:DataDrivenApproximation.pdf | A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition]], ''J. Nonlinear Science'', vol. 25, 2015.<br />
* D. Giannakis, [[Media:DataDrivenSpectralDecomposition.pdf | Data-Driven Spectral Decomposition and Forecasting of ergodic dynamical systems]], ''arXiv:1507.02338v2''<br />
* I. Mezic and A. Surana, [[Media:PeriodicKoopmanModeDecomposition.pdf | Koopman Mode Decomposition for Periodic/Quasi-Periodic Time Dependence]], ''IFAC Papers Online, 48-18, pp. 690697, 2016.<br />
* H. Schaeffer, [[Media:LearningPDEs.pdf | Learning Partial Differential Equations via Data Discovery and Sparse Optimization]], ''J. Royal Society, Proceedings A'', 2017<br />
* J.N. Kutz, X. Fu, S.L. Brunton, [[Media:MultiresolutionDMD.pdf | Multi-resolution Dynamic Mode Decomposition]], ''arXiv:1506.00564''<br />
<br />
==== Papers which are more oriented toward control ====<br />
* D. Goswami and D.A. Paley, [[Media:GlobalBilinearization.pdf | Global Bilinearization and Controllability of Control-Affine Nonlinear Systems: A Koopman Spectral Approach]],<br />
* A. Surana, [[Media:KoopmanObserverBasedSynthesis.pdf | Koopman Based Operator Synthesis for Control-Affine Noninear Systems]], ''Proc. IEEE Conf. Decision and Control'', 2016<br />
* A. Surana and A. Banaszuk, [[Media:LinearObserverSynthesis.pdf | Linear Observer Synthesis for Nonlinear Systems Using Koopman Operator Framework]], ''IFAC Papers Online'', 49-18, pp. 716-723, 2016.<br />
* E. Kaiser, N. Kutz, and S. Brunton, [[Sparse identification of nonlinear dynamics for model predictive control in the low-data limit]] ''arXiv preprint'' arXiv:1711.05501 (2017).<br />
<br />
==== Papers which are more oriented toward fluids ====<br />
* I. Mezic, [[Media:AnalysisFluidFlows.pdf | Analysis of Fluid Flows via Spectral Properties of the Koopman Operator]], ''Annual Review of Fluids,'' vol. 45, 357-378, 2013.<br />
* C.W. Rowley and S.T.M. Dawson, [[Media:FlowModelReductionReview.pdf | Model Reduction for Flow Analysis and Control]], ''Annual Review Fluids'', 49:387-417, 2017.<br />
* M.S Hemati, C.W. Rowley, E.A. Deem, L.N. Cattafesta, [[Media:DebiasingDMD.pdf | De-biasing the Dynamic Mode Decomposition for applied Koopman spectral analysis of noisy data sets]], ''arXiv:1502.03854v2''<br />
* J.H. Tu, [[Media:DMDApplicationsTheory.pdf | Dynamic Mode Decomposition, Theory and Applications]], Ph.D. Thesis, Princeton, 2013.<br />
* S Bagheri, [[Media:ShearFlowsThesis.pdf | Analysis and Control of Transitional Shear Flows Using Global Modes]], Ph.D. Thesis, Royal Inst. Technology, Sweden, 2010.<br />
<br />
==== Some Early Papers ====<br />
* Koopman's original paper: [[Media:KoopmanPNAS.pdf | Dynamical Systems of Continuous Spectra]], ''PNAS'' , vol. 18, 1932.<br />
* J. Ding, [[Media:PointSpectrum.pdf | The Point Spectrum of Frobenius-Perron and Koopman Operators]], ''Proc. AMS,'' vol. 126, no. 5, 1998.<br />
* I. Mezic and A. Banaszuk, [[Media:ComparisonSystems.pdf | Comparison of Systems with Complex Behavior]], ''Physica D'', vol. 197, pp. 101-133, 2004.<br />
* Y. Lan and I. Mezic, [[Media:LinearizationInTheLarge.pdf | Linearization in the Large of Nonlinear Systems and Koopman Operator Spectrum]], ''Physica D'', 2013<br />
<br />
==== Other Papers ====<br />
* E.Berger, M. Sastuba, D. Vogt, B. Jung, H.B. Amor, [[Media:EstimationRobotPerturbations.pdf | Estimation of Perturbations in Robotic Behavior using Dynamic Mode Decomposition]], ''Advanced Robotics,'' vol. 25, no. 5, 2015.<br />
* S. Wang, Z. Qiao, [[Media:NuclearNormDMD.pdf | Nuclear Norm Regularized Dynamic Mode Decomposition]], ''IET Signal Processing'', 2016.</div>Dpastormhttp://robotics.caltech.edu/wiki/index.php?title=ME_CS_133_2017-18&diff=1159ME CS 133 2017-182017-11-16T17:27:44Z<p>Dpastorm: /* Announcements For ME/CS 133(a,b) */</p>
<hr />
<div>This is the homepage for ME/CS 133(a,b) (Introduction to Robotics) for Fall/Winter 2017-18. <br />
__NOTOC__<br />
== Course Staff, Hours, Location ==<br />
<br />
{| border=1 width=100%<br />
|-<br />
| '''Position''' || '''Name''' || '''Office''' || '''Office Hours''' (changing weekly) || '''Email''' || '''Phone'''<br />
|-<br />
| '''Instructor'''<br />
| Joel Burdick<br />
| 245 Gates-Thomas<br />
| ''send mail for an appointment''<br />
| [mailto:jwb@robotics.caltech.edu jwb at robotics dot caltech dot edu]<br />
| 626-395-4139<br />
|-<br />
| '''Teach Asst.'''<br />
| Joseph Bowkett<br />
| 205 Gates-Thomas<br />
| TBD<br />
| [mailto:jbowkett@caltech.edu jbowkett at caltech dot edu]<br />
| 626-395-4470<br />
|-<br />
| '''Teach Asst.'''<br />
| Daniel Pastor Moreno<br />
| 205 Gates-Thomas<br />
| TBD<br />
| [mailto:dpastorm@caltech.edu dpastorm at caltech dot edu]<br />
| 626-395-4470<br />
<br />
|-<br />
| '''Teach Asst.'''<br />
| Jeff Edlund<br />
| 205 Gates-Thomas<br />
| TBD<br />
| [mailto:jedlund@caltech.edu jedlund at caltech dot edu]<br />
| 626-395-4470<br />
|-<br />
<br />
|-<br />
| '''Teach Asst.'''<br />
| Ellen Feldman<br />
| 205 Gates-Thomas<br />
| TBD<br />
| [mailto:efeldman@caltech.edu efeldman at caltech dot edu]<br />
| 626-395-4470<br />
|-<br />
<br />
|-<br />
| '''Teach Asst.'''<br />
| Luke Urban<br />
| 205 Gates-Thomas<br />
| TBD<br />
| [mailto:lsurban@gmail.com lsurban at gmail dot com]<br />
| 626-395-4470<br />
|-<br />
<br />
| '''Teach Asst.'''<br />
| Daniel Naftalovich <br />
| 205 Gates-Thomas<br />
| TBD<br />
| [mailto:nafty@caltech.edu nafty at caltech dot edu]<br />
| 626-395-4470<br />
<br />
|-<br />
| '''Administrative'''<br />
| Sonya Lincoln<br />
| 250 Gates-Thomas<br />
| 7:30am-noon; 1:00pm-4:30pm<br />
| [mailto:lincolns@caltech.edu lincolns at caltech dot edu]<br />
| 626-395-3385<br />
|}<br />
<br />
<br />
'''Lecture Schedule:''' <br />
* '''Days:''' Monday, Wednesday, Friday<br />
* '''Time:''' 3:00-3:55 pm <br />
* '''Location:''' 135 Gates-Thomas<br />
<br />
== Announcements For ME/CS 133(a,b) ==<br />
* '''11/16/17:''' Extra Office hours for Lab #1 are <br />
** 11/16/17 from 6:00-7:00 pm in SFL 326<br />
* '''11/13/17:''' Lab 1 has been corrected and simplified. See the [[Media:Lab1corrected.pdf | New Corrected Version of Lab 1]]<br />
* '''11/13/17:''' Office hours for Lab #1 are <br />
** 11/13/17 from 6:30-7:30 in SFL 326<br />
** 11/14/17 from 7-8 pm in SFL 231<br />
* '''10/13/17:''' Office hours for Homework #2<br />
* Monday, Oct. 16, '''4:00 pm''' (after class, in Room 135 Gates-Thomas)<br />
* Tuesday, Oct. 17, '''7:00-9:00 pm''' (room, 326 Sherman Fairchild)<br />
'''10/11/17:''' Homework #2 is due Wednesday, October 18 (see link below)<br />
'''10/04/17:''' Office hours for Homework 1 are:<br />
* 4:00 pm-5:00 pm (right after class) on Friday, '''Oct. 6''' in Gates-Thomas 135<br />
* 7:00 pm-10:00 pm Sunday, '''Oct. 8''', Sherman Fairchild Rooms 231 and 229<br />
'''10/02/17:''' Homework 1 was distributed in class on Monday, and is available at the link below. It is due at 5:00 pm on Monday, Oct. 9, 2017.<br />
<br />
== Course Lecture Schedule for ME/CS 133(a) ==<br />
{| border=1 width=100%<br />
|-<br />
| Week || Date || Topic || Reading || Optional Reading || Homework<br />
<br />
|-<br />
| align=center rowspan=4 | 1 <br />
| colspan=5|<br />
=====Introduction and Review of Rigid Body Kinematics =====<br />
|-<br />
| 25 Sept. (Mon.)<br />
| Class Overview<br />
| [[Media:MECS_133_overview_2017.pdf | Course Overview]], <br> [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page Chapter 1 of MLS]<br />
| [http://dlxs2.library.cornell.edu/k/kmoddl/pdf/013_002.pdf History of Kinematics Through 1900] (Introductory chapter from <em> Kinematic Synthesis of Linkages</em>) <br />
| rowspan=3 align=center | -No Homework-<br />
<br />
|-<br />
| 27 Sept. (W)<br />
| Planar Rigid Body Kinematics, <br> Planar displacements<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS Ch 2.1], Pages 19-23<br />
| [https://en.wikipedia.org/wiki/Peaucellier%E2%80%93Lipkin_linkage Wikepedia Page on the Peaucellier Mechanism]<br />
<br />
|-<br />
| 29 Sept. (F)<br />
| Planar Rigid Body Displacements (''continued''), <br> Displacement groups <br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS Ch 2.1], <br><br />
[[Media:PlanarDisplacements.pptx | Change of Reference in Planar Displacements]] (PowerPoint)<br />
| -N/A-<br />
<br />
|-<br />
| align=center rowspan=4 | 2<br />
| colspan=5 |<br />
<br />
===== From Planar Rigid Body Kinematics to Spherical Kinematics =====<br />
|-<br />
| 02 Oct. (M)<br />
| poles, [http://robotics.caltech.edu/~jwb/courses/ME115/Lectures/Centrodes.pptx Centrodes], elliptic Trammel <br> <br />
| [[Media:EllipticalTrammel.pdf | Notes on the Elliptical Trammel]]<br />
| [http://en.wikipedia.org/wiki/Trammel_of_Archimedes Archemides Trammel] (Wikipedia)<br>[https://www.youtube.com/watch?v=CBhxKavV_Xo Trammel], [https://www.youtube.com/watch?v=OMNArJh7umg&list=PL6534E936D46257BF&index=22 V 1], [https://www.youtube.com/watch?v=GAVx3x_H1eA&list=PL6534E936D46257BF&index=20# V 2], [https://www.youtube.com/watch?v=OMNArJh7umg&list=PL6534E936D46257BF&index=22 compliation], <br> [[Media:PolyhedralLinkages.pdf | Linkages Synthesized Using Cardan Motion Along Radial Lines]]<br />
| rowspan=3 align=center | [[Media:MECS133a_set1.17.pdf | Homework 1]], <br> (Due Oct. 9) <br> [[Media:MECS133_sol1.17.pdf | Solution 1]] <br> [[Media:Homework1Grades.pdf | Histogram of grades received on Hwk 1]]<br />
<br />
|-<br />
| 04 Oct. (W)<br />
| Intro to Spherical Kinematics <br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS Pages 22-26],<br> [[Media:MatrixGroups.pdf | Notes on the Classical Matrix Groups]]<br />
| -N/A-<br />
<br />
|-<br />
| 06 Oct. (F)<br />
| Spherical Kinematics (''continued''), <br> Classical Matrix Groups<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS Ch 2.2, 2.3], <br> [[Media:rotation.pdf | Notes on Rotations]]<br />
| [http://www.fulviofrisone.com/attachments/article/486/Weyl%20-%20The%20Classical%20Groups%20(168S).pdf Herman Weyl's book on the classical groups]<br />
<br />
|-<br />
| align=center rowspan=4 | 3<br />
| colspan=5 |<br />
<br />
===== Spherical Kinematics =====<br />
|-<br />
| 9 Oct. (M)<br />
| Cayley's Theorem, Euler's Theorem<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 27-31]<br />
| [https://en.wikipedia.org/wiki/Cayley_transform Wikipedia Page on Cayley Transform]<br />
| rowspan=3 align=center | [[Media:MECS133a_set2a.17.pdf | Homework 2]] <br> (Due Oct. 18) <br> [[Media:MECS133_sol2.17.pdf | Solution 2]]<br />
|-<br />
| 11 Oct. (W)<br />
| Angle-Axis Representation, Rodriguez Formula, Matrix Exponential, <br />
| <br />
| -N/A-<br />
|-<br />
| 13 Oct. (F)<br />
| Euler Angles<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 31-34] <br />
| -N/A-<br />
<br />
|-<br />
| align=center rowspan=4 | 4<br />
| colspan=5 |<br />
<br />
===== Spherical Kinematics =====<br />
|-<br />
| 16 Oct. (M)<br />
| Quaternions<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 33-34]<br />
| [[Media:NotesOnAlgebras.pdf | Notes On Algebras]] <br />
| rowspan=3 align=center | -N/A-<br />
|-<br />
| 18 Oct. (W)<br />
| Quaternion Wrap-Up, <br> Intro to Spatial Kinematics, <br> Homogeneous Coordinates, <br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 34-39]<br />
| -N/A-<br />
|-<br />
| 20 Oct. (F)<br />
| Spatial Exponential Coordinates, <br> Intro to screws<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 39-45] <br> [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 45-50]<br />
| -N/A-<br />
<br />
<br />
|-<br />
| align=center rowspan=4 | 5<br />
| colspan=5 |<br />
<br />
===== Spatial Kinematics and Velocities =====<br />
|-<br />
| 23 Oct. (M)<br />
| Motion Capture via Rodriguez Equation <br> Intro to Rigid Body Velocities <br />
| [[Media:Rodriguez.pdf | Using Rodriguez' Displacement Equation]], <br>[http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 51-56]<br />
| <br />
| rowspan=3 align=center | [[Media:MECS133a_set3.pdf | Homework 3]] <br> [[Media:VirualMachineSetup.pdf | Instructions on Acquiring Virtual Machine]] <br> [http://robotics.caltech.edu/~jbowkett/me133a_lab1.py Python script for lab 1] <br> [[Media:ROS_tutorial.pdf | ROS Tutorial]] <br> [[Media:MECS133_sol3_17.pdf | Solution 3]]<br />
|-<br />
| 25 Oct. (W)<br />
| Rigid Body Velocities Continued <br> Intro to Wrenches <br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 57-64]<br />
| -N/A-<br />
|-<br />
| 27 Oct. (F)<br />
| ''No Class'' <br />
| <br />
| -N/A-<br />
<br />
|-<br />
| align=center rowspan=4 | 6<br />
| colspan=5 |<br />
<br />
===== Spatial Kinematics and Velocities =====<br />
|-<br />
| 30 Oct. (M)<br />
| Rigid Body Velocities and Coordinate Transformations <br />
| [[Media:Rodriguez.pdf | Using Rodriguez' Displacement Equation]], <br>[http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 51-56]<br />
| <br />
| rowspan=3 align=center | [http://robotics.caltech.edu/~jbowkett/me133a_lab2.py Python script for ROS Tutorial & Lab 2] <br> <br />
|-<br />
| 1 Nov. (W)<br />
| ROS Tutorial<br />
| [[Media:ROS_tutorial.pdf | ROS Tutorial]]<br />
| -N/A-<br />
|-<br />
| 3 NOV. (F)<br />
| Turtlebot Tutorial <br />
| <br />
| -N/A-<br />
<br />
|-<br />
| align=center rowspan=4 | 7<br />
| colspan=5 |<br />
<br />
===== Spatial Kinematics and Intro to Linkages =====<br />
|-<br />
| 6 Nov. (M)<br />
| Rigid Body Velocities Reviewed, Wrenches<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 61-66]<br />
| <br />
| rowspan=3 align=center | [[Media:Lab1corrected.pdf | Lab 1 (corrected): Motion Capture]] <br> [[Media:me133a_6nov_wand_250_270m.csv | me133a_6nov_wand_250_270m.csv]]; <br> [http://robotics.caltech.edu/~jwb/courses/MECS133/optiTrack_matlab_template.m optitrack_matlab_template.m] <br> Due Fri. Nov. 17 <br> [http://robotics.caltech.edu/~jbowkett/OptitrackAnalysis_template.py Optitrack Python Analysis Template]<br />
|-<br />
| 8 Nov. (W)<br />
| Intro to Kinematics of Linkages and Manipulators<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 81-90]<br />
| -N/A-<br />
|-<br />
| 10 Nov. (F)<br />
| Denavit Hartenberg Parameters<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 81-90]<br />
| -N/A-<br />
<br />
<br />
|-<br />
| align=center rowspan=4 | 8<br />
| colspan=5 |<br />
<br />
===== Linkges and Forward Kinematics=====<br />
|-<br />
| 13 Nov. (M)<br />
| ABET interview <br> Denavit-Hartenberg Continued, <br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 81-94]<br />
| <br />
| rowspan=3 align=center | -N/A- <br />
|-<br />
| 15 Nov. (W)<br />
| Product of Exponentials<br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS 81-94]<br />
| -N/A-<br />
|-<br />
| 17 Nov. (F)<br />
| Kinematics of Wheeled Vehicles<br />
| -N/A-<br />
| -N/A-<br />
<br />
<br />
|}<br />
<br />
== Course Text and References ==<br />
<br />
The '''main course text''' for '''ME/CS 133(a)''' is: <br />
* [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page R.M. Murray, Z. Li, and S. Sastry, ''A Mathematical Introduction to Robotic Manipulation,'' CR Press, 1994.] <br />
* The 1st edition of this book is available freely on-line at the link above, and is perfectly adequate for the course<br />
<br />
We will refer to this text as ''MLS'' (the initials of the authors' last names). While the course topics will follow the text, additional material will often be presented in class. Additional course handouts covering this material will be posted on this website<br />
<br />
A ''' main text''' for the '''ME/CS 133(b)''' is: ''Planning Algorithms'' by Steve LaValle (UIUC). <br />
* You can buy this book [http://www.amazon.com/Planning-Algorithms-Steven-M-LaValle/dp/0521862051/sr=1-1/qid=1167872270/ref=sr_1_1/105-3129515-7885245?ie=UTF8&s=books on-line at Amazon]. A [http://msl.cs.uiuc.edu/planning/ preprint of the text ] is available freely on-line, and is adequate for all course activities. <br />
<br />
The following book is recommended (but not required) for ME/CS 133(b):<br />
* ''Principles of Robot Motion: Theory, Algorithms, and Implementations,'' by Howie Choset, Kevin Lynch, Seth Hutchinson, George Kantor, Wolfram Burgard, Lydia Kavraki, and Sebastian Thrun. <br />
<br />
This text is [http://www.amazon.com/Principles-Robot-Motion-Implementations-Intelligent/dp/0262033275/sr=1-2/qid=1167872622/ref=sr_1_2/105-3129515-7885245?ie=UTF8&s=books available at Amazon ]<br />
in both new and used versions.<br />
<br />
=== Grading ===<br />
<br />
The final grade will be based on homework sets, and a final exam or final project: <br />
<br />
* ''' Homework (40%):''' Homework sets are due at 5 pm on the due date (which will always coincide with a class meeting). Homeworks can be dropped off in class, or deposited in the box outside of 245 Gates-Thomas. Some homeworks will require computation. MATLAB or Mathematica should be sufficient to solve every homework posed in ME/CS 133(a), though students can choose their favorite programming language. Code is considered part of your solution and should be included in with the problem set when appropriate.<br />
<br />
* ''' Laboratory (30%):''' Lab reports are due at 5 pm on the due date (which will usually coincide with a class meeting). Labs can be dropped off in class, or deposited in the box outside of 245 Gates-Thomas. The first labs will familiarize students with the class robots. Subsequent labs will focus on how to translate the lecture material to the lab robots, and will often involve the use of software systems such as ROS and OOMPL.<br />
<br />
* '''Final exam/project (30%):''' In ME/CS 133(a), students have the option to take a final exam (a limited time take-home format exam which is open book, open note, and computer allowed) or select a final project. The final project must incorporate some aspect of the course, and the topic and scope my be approved by the course instructor. The final exam will due at 5:00 pm the last day of finals. The final project is similarly due at 5:00 pm on the last day of finals.<br />
<br />
* '''Late Homework Policy:''' Students may automatically take a 2-day extension on '''two''' homeworks or labs during each quarter.<br />
<br />
=== Collaboration Policy === <br />
<br />
Collaboration on homework assignments is encouraged. You may consult outside reference materials, other students, the TA, or the instructor, but you must cite any use of material from outside references. All solutions that are handed in should be written up individually and should reflect<br />
your own understanding of the subject matter. Computer code and graphical plots are considered part of your solution, and therefore should be done individually (you can share ideas, but not code). No collaboration is allowed on the examinations.</div>Dpastormhttp://robotics.caltech.edu/wiki/index.php?title=ME_CS_132_2017&diff=825ME CS 132 20172017-02-23T21:58:33Z<p>Dpastorm: </p>
<hr />
<div>This is the homepage for ME/CS 132(a,b) (Advanced Robotics: Navigation and Vision) for Winter/Spring 2017. <br />
__NOTOC__<br />
== Course Staff, Hours, Location ==<br />
<br />
{| border=1 width=100%<br />
|-<br />
| '''Position''' || '''Name''' || '''Office''' || '''Office Hours''' (changing weekly) || '''Email''' || '''Phone'''<br />
|-<br />
| '''Instructor'''<br />
| Joel Burdick<br />
| 245 Gates-Thomas<br />
| ''send mail for an appointment''<br />
| [mailto:jwb@robotics.caltech.edu jwb at robotics dot caltech dot edu]<br />
| 626-395-4139<br />
|-<br />
| '''Teach Asst.'''<br />
| Joseph Bowkett<br />
| 205 Gates-Thomas<br />
| TBD<br />
| [mailto:jbowkett@caltech.edu jbowkett at caltech dot edu]<br />
| 626-395-1989<br />
|-<br />
| '''Teach Asst.'''<br />
| Daniel Pastor Moreno<br />
| 205 Gates-Thomas<br />
| TBD<br />
| [mailto:dpastorm@caltech.edu dpastorm at caltech dot edu]<br />
| 626-395-1989<br />
<br />
|-<br />
| '''Teach Asst.'''<br />
| Yoke Peng Leong<br />
| Annenberg<br />
| TBD<br />
| [mailto:ypleong@caltech.edu ypleong at caltech dot edu]<br />
| 626-395-????<br />
<br />
|-<br />
| '''Administrative'''<br />
| Sonya Lincoln<br />
| 250 Gates-Thomas<br />
| 7:30am-noon; 1:00pm-4:30pm<br />
| [mailto:lincolns@caltech.edu lincolns at caltech dot edu]<br />
| 626-395-3385<br />
|}<br />
<br />
<br />
'''Lecture Schedule:''' Based on a vote in class, for the near future we will meet at these times and locations:<br />
* '''Wednesday:''' 7:30-10:30 pm. Room 135 Gates-Thomas<br />
<br />
'''Note:''' As the course enrollment firms up, we will vote one more time to see if we can find a better meeting time.<br />
<br />
== Announcements For ME/CS 132(a,b) ==<br />
* '''02/22/17:''' [[Media:MECS132_FinalProject2017.pdf | Final Project Guidelines]] are available<br />
* '''02/13/17:''' Office Hours for Homework #3 will be held 6-7 pm on Wed., Feb 15 in 220 SFL, and 4:00-5:30 pm on Thurs., Feb 16 in 231 SFL<br />
* '''02/01/17:''' Office Hours for Homework #2 will be held 7:30-9:00 pm on Thurs., Feb. 1 in 135 Gates-Thomas<br />
* '''01/22/17:''' Office Hours for Hmmeowrk #1 will be held 8-10 pm on Sunday, Jan. 22 in 135 Gates-THomas.<br />
* '''01/05/17:''' The meeting time and place have been set for the class lectures.<br />
* '''01/04/17:''' The permanent lecture hours and location will be determined at the course organizational meeting.<br />
<br />
== Course Text and References ==<br />
<br />
1) The main text for the first half of the course is:<br />
* ''Planning Algorithms'' by Steve LaValle (UIUC). <br />
<br />
You can buy this book [http://www.amazon.com/Planning-Algorithms-Steven-M-LaValle/dp/0521862051/sr=1-1/qid=1167872270/ref=sr_1_1/105-3129515-7885245?ie=UTF8&s=books on-line at Amazon]. A [http://msl.cs.uiuc.edu/planning/ preprint of the text ] is available freely on-line, and is adequate for all course activities. <br />
<br />
2) The following book is recommended (but not required):<br />
* ''Principles of Robot Motion: Theory, Algorithms, and Implementations,'' by Howie Choset, Kevin Lynch, Seth Hutchinson, George Kantor, Wolfram Burgard, Lydia Kavraki, and Sebastian Thrun. <br />
<br />
This text is [http://www.amazon.com/Principles-Robot-Motion-Implementations-Intelligent/dp/0262033275/sr=1-2/qid=1167872622/ref=sr_1_2/105-3129515-7885245?ie=UTF8&s=books available at Amazon ]<br />
in both new and used versions.<br />
<br />
3) Interested students may wish to also consult the following classic (but now out-of-print) text on motion planning: ''Robot Motion Planning'' by J.C. Latombe. A copy is available in the Caltech library.<br />
<br />
== Course Lecture Schedule for ME/CS 132(a) ==<br />
<br />
{| border=1 width=100%<br />
|-<br />
| Week || Date || Topic || Reading || Optional Reading || Homework<br />
<br />
|-<br />
| align=center rowspan=3 | 1 <br />
| colspan=5|<br />
=====Introduction and Review of Rigid Body Kinematics =====<br />
<br />
|-<br />
| 4 Jan (Wed.)<br />
| Class Overview & Mechanics <br> The basic motion planning problem<br />
| [[Media:ME_CS_132_CourseOverview.pdf | Course Overview]]<br />
| [http://msl.cs.uiuc.edu/planning/ch1.pdf Chapter 1 of Lavalle]<br />
| rowspan=2 align=center | -No Homework-<br />
<br />
|-<br />
| 6 Jan (Fri.)<br />
| Review of Motion Planning Problems and Issues<br />
| <br />
| <br />
<br />
|-<br />
| align=center rowspan=3 | 2<br />
| colspan=5 |<br />
===== Intro to C-space and the Basic Motion Planning Problem =====<br />
<br />
|-<br />
| 11 Jan (W)<br />
| Configuration Space (C-space) <br> Review of Planar Rigid Body Kinematics <br />
| Lavalle 4.2.1; Lavalle Chapter 3.2.2 (pages 94-97) <br> [[Media: CObstacleNotes.pdf | Notes on C-obstacles]]; [[Media:StarAlgorithm.pdf | The Star Algorithm]]; <br />
| [http://www.cds.caltech.edu/~murray/mlswiki/index.php/Main_Page MLS Ch 2.1], Pages 19-23 <br> Lavalle Chapter 3.1<br />
| rowspan=2 align=center | [[Media:ME_CS_132_2016_Homework1.pdf | Homework 1]], <br> [[Media:ME_CS_132_2016_Solution1.pdf | Solution 1]]<br />
<br />
|-<br />
| 13 Jan (F)<br />
| Configuration-Space Obstacles <br />
| Lavalle Chapter 4.3 <br> [[Media:CObstacle_Param.pdf | Notes on Parametrized C-obstacles]]<br />
| [[Media:EllipseCObstacle.pdf | Picture of C-Obstacle]]; [https://www.youtube.com/watch?v=SBFwgR4K1Gk C-space Visualization Video];[http://demonstrations.wolfram.com/RobotMotionWithObstacles/ Mathematica Demo of Manipulator C-Obstacles];<br />
<br />
|-<br />
| align=center rowspan=2 | 3<br />
| colspan=5 |<br />
<br />
===== C-obstacles and the Classical Motion Planning Algorithms =====<br />
<br />
|-<br />
| 18 Jan (W)<br />
| Computing C--space obstacles <br> Review of Classical Motion Planning Algorithms <br> The Road Map <br />
| Lavalle 4.3 (pages 155-167) <br> Lavalle 6.1, Lavalle 6.2 (focusing on roadmaps)<br />
|<br />
| rowspan=1 align=center | No Homework Assigned<br />
<br />
|-<br />
| align=center rowspan=2 | 4<br />
| colspan=5 |<br />
===== Roadmap Motion Planning Algorithms =====<br />
<br />
|-<br />
| 25 Jan (W)<br />
| The Road Map (continued) <br> Intro to Potential Field Methods<br />
| Lavalle 6.1, Lavalle 6.2 (focusing on roadmaps)<br />
|<br />
| rowspan=1 align=center | [[Media:Homework2.pdf | Homework #2]] <br> [[Media:ME132_VM_Setup.pdf | Instructions for OMPL and ROS Virtual Machine Setup]]<br />
<br />
|-<br />
| align=center rowspan=2 | 5<br />
| colspan=5 |<br />
<br />
===== Potential Field and Cellular Decomposition Algorithms =====<br />
<br />
|-<br />
| 1 Feb (W)<br />
| Potential Fields continued <br> Cellular Decomposition Methods <br />
| Lavalle 6.3 (Cellular Decompositions)<br />
|<br />
| rowspan=1 align=center | No Homework Assigned<br />
<br />
|-<br />
| align=center rowspan=2 | 6<br />
| colspan=5 |<br />
<br />
===== Sampling Based Methods and Graphs Search Algorithms =====<br />
<br />
|-<br />
| 8 Feb (W)<br />
| Sampling Based Planning Methods <br> Brief Tutorial on Graph Searching<br />
| Lavalle, Sections 5.2-5.5 (Samplinlg Based Methods) <br> Lavalle, Section 2.1 and 2.2 <br> [[Media:Astar.pdf | Notes on A-star]]<br />
|<br />
| rowspan=1 align=center | [[Media:Homework3.pdf | Homework #3]] <br> [[Media:ME132_Lab2.pdf | Instructions for Lab 2]] <br> [http://robotics.caltech.edu/~jbowkett/me132_lab2.tar.gz Files for Lab 2]<br />
<br />
|-<br />
| align=center rowspan=2 | 7<br />
| colspan=5 |<br />
<br />
===== Graphs Search (continued), Sensor-Based Motion Planning =====<br />
<br />
|-<br />
| 15 Feb (W)<br />
| A-Star & Dijkstra Graph Search <br> Bug Algorithms<br />
| [[Media:Astar.pdf | Notes on A-star]]; [[Media:AstarAnalysis.pdf | Analysis of A-Star]] <br> [[Media:BugSlides.pdf | Choset Slides on Bug Algorithms ]] <br> Lavalle 667-673<br />
| [http://robotics.caltech.edu/~jwb/courses/ME132/handouts/LumelskyBug.pdf Lumelsky Bug Algorithm Paper]<br />
| -N/A-<br />
<br />
|-<br />
| align=center rowspan=2 | 9<br />
| colspan=5 |<br />
<br />
===== Sensor-Based Motion Planning (continued) =====<br />
<br />
|-<br />
| 15 Feb (W)<br />
| Tangent Bug Algorithm, Sensorized GVD, D*-Algorithm<br />
| [[Media:BugSlides.pdf | Choset Slides on Bug Algorithms ]] <br> Lavalle 667-673<br />
| <br />
| [[Media:Homework4.zip | Homework #4]]<br />
<br />
|}<br />
<br />
== Course Mechanics, Grading, and Collaboration Policy ==<br />
<br />
=== Grading ===<br />
<br />
The final grade will be based on homework sets, and a final exam or final project: <br />
<br />
* ''' Homework (70%):''' Homework sets will be handed out every 7-10 days, and are due at 5 pm on the due date (which will always coincide with a class meeting). Homeworks can be dropped off in class, or deposited in the box outside of 245 Gates-Thomas. Some homeworks will require computation. MATLAB or Mathematica should be sufficient to solve every homework posed in this course, though students can choose their favorite programming language. Code is considered part of your solution and should be included in with the problem set when appropriate.<br />
<br />
* '''Final exam/project (30%):''' Students have the option to take a final exam (a limited time take-home format exam which is open book, open note, and computer allowed) or select a final project. The final project must incorporate some aspect of the course, and the topic and scope my be approved by the course instructor. The final exam will due at 5:00 pm the last day of finals. The final project is similarly due at 5:00 pm on the last day of finals.<br />
<br />
* '''Late Homework Policy:''' Students may automatically take a 2-day extension on '''two''' homeworks during each quarter.<br />
<br />
=== Collaboration Policy === <br />
<br />
Collaboration on homework assignments is encouraged. You may consult outside reference materials, other students, the TA, or the instructor, but you must cite any use of material from outside references. All solutions that are handed in should be written up individually and should reflect<br />
your own understanding of the subject matter. Computer code and graphical plots are considered part of your solution, and therefore should be done individually (you can share ideas, but not code). No collaboration is allowed on the examinations.</div>Dpastorm