SlideShare une entreprise Scribd logo
1  sur  30
Télécharger pour lire hors ligne
Learning Dynamical Systems
from Demonstrations
0
Organizers/Speakers: Nadia Figueroa, Sina Mirrazavi, Lukas Huber,
Aude Billard
Representing Robot Motions with an
Autonomous Dynamical System (DS)
Velocity Position Target
Variables
1
Representing Robot Motions with an
Autonomous Dynamical System (DS)
Velocity Position Target
Variables
Target
1x
2x
x
Lyapunov Theorem for
Global Asymptotic Stability
How to ensure convergence to
the desired target?
2
Global Asymptotic Stability of
Autonomous Dynamical System (DS)
Lyapunov Function ~ Energy-like Function
Theorem A DS is globally asymptotically stable at iff
there exists a Lyapunov candidate function
that is radially unbounded; i.e. and
satisfies the following conditions:
V should be non-increasing along all trajectories.
Lyapunov’s Theorem for Global Asymptotic Stability
3
Lyapunov’s Theorem for Global Asymptotic Stability
Level Sets of Lyapunov Function
Theorem A DS is globally asymptotically stable at iff
there exists a Lyapunov candidate function
that is radially unbounded; i.e. and
satisfies the following conditions:
V should be non-increasing along all trajectories.
Global Asymptotic Stability of
Autonomous Dynamical System (DS)
4
Obtuse Angle
Stability of a Linear Autonomous Dynamical System (DS)
Quadratic Lyapunov Function (QLF)
How to ensure is always negative?
Enforce the eigenvalues to be negative! 5
Stability of a Linear Autonomous Dynamical System (DS)
Parametrized Quadratic Lyapunov Function (P-QLF)
Enforce the eigenvalues to be negative!
What if f(x) is non-linear?
Stability not easy to define: local linearization;
numerical estimation of stability;
analytical solution in special cases. 6
Representing Non-linear Motions as Mixtures of Linear DS
7
2-nd Linear DS
4-th Linear DS Activation/Mixing
function for 2-nd DS
Activation/Mixing
function for 4-th DS
How do we learn all of
these parameters?
8
Learning Non-linear DS via Gaussian Mixture Regression
Take a density based approach to modeling dynamical systems
Given a set of demonstrations, learn the joint density via GMM
2D projection of a
normal distribution
   ~ ; ,p x N x  
9
Learning Non-linear DS via Gaussian Mixture Regression
Through a slight change of variables To ensure Global Asymptotic Stability
Khansari Zadeh, S. M. and Billard, A. (2011) IEEE Transactions on Robotics
We estimate the Gaussian parameters via constraint-
based optimization with stability constraints.
Stability Constraints
10
Learning Non-linear DS via Gaussian Mixture Regression
[1] Khansari Zadeh, S. M. and Billard, A. (2011) IEEE Transactions on Robotics
Stable Estimator of Dynamical Systems (SEDS) Approach [1]
Demonstrations
Reproductions
11
SEDS in Action
Khansari Zadeh, S. M. and Billard, A. (2011) IEEE Transactions on Robotics
Demonstrations of Point-to-Point Motions Execution of Learned DS Motions
12
SEDS in Action
[2] Figueroa, Pais and Billard. (2016) ACM/IEEE HRI Conference
Demonstrations of Sequence of Point-to-Point Motions Execution of Sequence of Learned DS Motions
Learn a point-to-point SEDS for each Phase + impedance/force profiles [2]
13
Limitations of SEDS Approach
 Optimal number of K Gaussian components has to be set manually or ‘empirically’
 Cannot handle highly non-linear motions:
Why can’t we model these trajectories accurately?
14
These trajectories violate this condition
QLF is too conservative.
Acute Angles!
Can we do better?
16
Acute Angles!
Use Parametrized Quadratic
Lyapunov Function (P-QLF)!
These trajectories violate this condition
QLF is too conservative.
Acute Angles!
17
Learning Non-linear DS via GMMs with P-QLF
We decouple the density estimation from the DS parameters
Given a set of demonstrations, learn the
GMM density on position variables only Solve a constrained optimization problem
Stability Constraints
Ensure Stability with P-QLF
18
Learning Non-linear DS via GMMs with P-QLF
[3] Mirrazavi, BIllard. (2018) EPFL PhD Thesis.
Linear Parameter Varying (LPV) Dynamical Systems (DS) Approach [2]
19
Outperforms SEDS in Reproduction Accuracy
20
Outperforms SEDS in Reproduction Accuracy
21
Limitations of LPV-DS Approach
 Optimal number of K Gaussian components has to be set manually or ‘empirically’
 Very sensitive to GMM fit:
Good GMM fit
22
Limitations of LPV-DS Approach
 Optimal number of K Gaussian components has to be set manually or ‘empirically’
 Very sensitive to GMM fit:
Bad GMM fit
Other SEDS-based Extensions – beyond QLF
Tau-SEDS Approach [4]:
Based on Diffeomorphic Transformations
And Complex Lyapunov Functions
23[4] Neumann, Steil (2015) Robotics and Autonomous Systems
Step 1: Construct a Lyapunov Candidate
Function Consistent with the Demonstrations
Weighted Sum of Asymmetric
Quadratic Functions (WSAQF) [5]
[5] Khansari, Billard (2015) Robotics and Autonomous Systems
Other SEDS-based Extensions – beyond QLF
Tau-SEDS Approach [4]:
Based on Diffeomorphic Transformations
And Complex Lyapunov Functions
24
Step 2: Define a diffeomorphism where
takes the form of a QLF
Step 3: Transform the demonstrations via
Step 4: Learn SEDS on transformed data.
Step 1: Construct a Lyapunov Candidate
Function Consistent with the Demonstrations
[4] Neumann, Steil (2015) Robotics and Autonomous Systems [5] Khansari, Billard (2015) Robotics and Autonomous Systems
Other SEDS-based Extensions – beyond QLF
Tau-SEDS Approach [4]:
Based on Diffeomorphic Transformations
And Complex Lyapunov Functions
25
Step 2: Define a diffeomorphism where
takes the form of a QLF
Step 3: Transform the demonstrations via
Step 4: Learn SEDS on transformed data.
Step 5: Back-transform learn SEDS via
Step 1: Construct a Lyapunov Candidate
Function Consistent with the Demonstrations
[4] Neumann, Steil (2015) Robotics and Autonomous Systems [5] Khansari, Billard (2015) Robotics and Autonomous Systems
Other SEDS-based Extensions – beyond QLF
26
Contracting Dynamical Systems Primitives [5]
[6] Ravichandar, Salehi, Dani (2017) CoRL
Stability Constraints via
Partial Contraction Theory
Full List of Publications Mentioned in Lecture
27
[1] Khansari Zadeh, S. M. and Billard, A. (2011) Learning Stable Non-Linear Dynamical Systems with Gaussian
Mixture Models. IEEE Transaction on Robotics, vol. 27, num 5, p. 943-957.
[2] Figueroa, N., Pais, A. L. and Billard, A. (2016) Learning Complex Sequential Tasks from Demonstration: A
Pizza Dough Rolling Case Study. In Proc. of the 2016 ACM/IEEE International Conference on Human-Robot
Interaction. HRI Pioneers Workshop.
[3] Mirrazavi Salehian, S. S. (2018) Compliant control of Uni/ Multi- robotic arms with dynamical systems.
PhD Thesis.
[4] K. Neumann and J. J. Steil. (2015) Learning robot motions with stable dynamical systems under
diffeomorphic transformations. Robotics and Autonomous Systems, 70 (Supplement C):1 – 15
[5] Khansari Zadeh, S. M. and Billard, A. (2014) Learning Control Lyapunov Function to Ensure Stability of
Dynamical System-based Robot Reaching Motions. Robotics and Autonomous Systems
[6] H. Ravichandar, I. Salehi, and A. Dani. (2017) Learning partially contracting dynamical systems from
demonstrations. In Proceedings of the 1st Annual Conference on Robot Learning, vol. 78 of Proceedings of
Machine Learning Research, pp 369–378
Exercise Session 1
28
Selection of
number of
Gaussians
Selection of
Objective
Function
Exercise Session 1
29
Selection of
number of
Gaussians
Selection of
Optimization
Variant
Exercise Session 1
30
Selection of
Optimization
Variant
P is unknown, is estimated jointly with A’s.
P is known, it is estimated a priori via [5]
[5] Khansari, Billard (2015) Robotics and Autonomous Systems

Contenu connexe

Tendances

[DL輪読会]Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neu...
[DL輪読会]Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neu...[DL輪読会]Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neu...
[DL輪読会]Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neu...Deep Learning JP
 
(ICML2020 K.Kato et al. fujitsu) Rate distortion optimization guided autoenco...
(ICML2020 K.Kato et al. fujitsu) Rate distortion optimization guided autoenco...(ICML2020 K.Kato et al. fujitsu) Rate distortion optimization guided autoenco...
(ICML2020 K.Kato et al. fujitsu) Rate distortion optimization guided autoenco...Yoshiki Yamamoto
 
深層強化学習による自動運転車両の追い越し行動の実現に関する研究
深層強化学習による自動運転車両の追い越し行動の実現に関する研究深層強化学習による自動運転車両の追い越し行動の実現に関する研究
深層強化学習による自動運転車両の追い越し行動の実現に関する研究harmonylab
 
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
[DL輪読会]Dream to Control: Learning Behaviors by Latent ImaginationDeep Learning JP
 
スパースモデリング、スパースコーディングとその数理(第11回WBA若手の会)
スパースモデリング、スパースコーディングとその数理(第11回WBA若手の会)スパースモデリング、スパースコーディングとその数理(第11回WBA若手の会)
スパースモデリング、スパースコーディングとその数理(第11回WBA若手の会)narumikanno0918
 
[DL輪読会]“SimPLe”,“Improved Dynamics Model”,“PlaNet” 近年のVAEベース系列モデルの進展とそのモデルベース...
[DL輪読会]“SimPLe”,“Improved Dynamics Model”,“PlaNet” 近年のVAEベース系列モデルの進展とそのモデルベース...[DL輪読会]“SimPLe”,“Improved Dynamics Model”,“PlaNet” 近年のVAEベース系列モデルの進展とそのモデルベース...
[DL輪読会]“SimPLe”,“Improved Dynamics Model”,“PlaNet” 近年のVAEベース系列モデルの進展とそのモデルベース...Deep Learning JP
 
Deep Reinforcement Learning and Its Applications
Deep Reinforcement Learning and Its ApplicationsDeep Reinforcement Learning and Its Applications
Deep Reinforcement Learning and Its ApplicationsBill Liu
 
【DL輪読会】論文解説:Offline Reinforcement Learning as One Big Sequence Modeling Problem
【DL輪読会】論文解説:Offline Reinforcement Learning as One Big Sequence Modeling Problem【DL輪読会】論文解説:Offline Reinforcement Learning as One Big Sequence Modeling Problem
【DL輪読会】論文解説:Offline Reinforcement Learning as One Big Sequence Modeling ProblemDeep Learning JP
 
[DL輪読会]Deep Dynamics Models for Learning Dexterous Manipulation
[DL輪読会]Deep Dynamics Models for Learning Dexterous Manipulation[DL輪読会]Deep Dynamics Models for Learning Dexterous Manipulation
[DL輪読会]Deep Dynamics Models for Learning Dexterous ManipulationDeep Learning JP
 
[DL輪読会]"CyCADA: Cycle-Consistent Adversarial Domain Adaptation"&"Learning Se...
 [DL輪読会]"CyCADA: Cycle-Consistent Adversarial Domain Adaptation"&"Learning Se... [DL輪読会]"CyCADA: Cycle-Consistent Adversarial Domain Adaptation"&"Learning Se...
[DL輪読会]"CyCADA: Cycle-Consistent Adversarial Domain Adaptation"&"Learning Se...Deep Learning JP
 
Optimization and particle swarm optimization (O & PSO)
Optimization and particle swarm optimization (O & PSO) Optimization and particle swarm optimization (O & PSO)
Optimization and particle swarm optimization (O & PSO) Engr Nosheen Memon
 
はじめてのKrylov部分空間法
はじめてのKrylov部分空間法はじめてのKrylov部分空間法
はじめてのKrylov部分空間法tmaehara
 
ベイズ推論とシミュレーション法の基礎
ベイズ推論とシミュレーション法の基礎ベイズ推論とシミュレーション法の基礎
ベイズ推論とシミュレーション法の基礎Tomoshige Nakamura
 
Particle swarm optimization
Particle swarm optimizationParticle swarm optimization
Particle swarm optimizationSuman Chatterjee
 
ADVANCED OPTIMIZATION TECHNIQUES META-HEURISTIC ALGORITHMS FOR ENGINEERING AP...
ADVANCED OPTIMIZATION TECHNIQUES META-HEURISTIC ALGORITHMS FOR ENGINEERING AP...ADVANCED OPTIMIZATION TECHNIQUES META-HEURISTIC ALGORITHMS FOR ENGINEERING AP...
ADVANCED OPTIMIZATION TECHNIQUES META-HEURISTIC ALGORITHMS FOR ENGINEERING AP...Ajay Kumar
 
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recog...
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recog...Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recog...
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recog...yukihiro domae
 
Gradient descent optimizer
Gradient descent optimizerGradient descent optimizer
Gradient descent optimizerHojin Yang
 

Tendances (20)

[DL輪読会]Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neu...
[DL輪読会]Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neu...[DL輪読会]Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neu...
[DL輪読会]Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neu...
 
(ICML2020 K.Kato et al. fujitsu) Rate distortion optimization guided autoenco...
(ICML2020 K.Kato et al. fujitsu) Rate distortion optimization guided autoenco...(ICML2020 K.Kato et al. fujitsu) Rate distortion optimization guided autoenco...
(ICML2020 K.Kato et al. fujitsu) Rate distortion optimization guided autoenco...
 
深層強化学習による自動運転車両の追い越し行動の実現に関する研究
深層強化学習による自動運転車両の追い越し行動の実現に関する研究深層強化学習による自動運転車両の追い越し行動の実現に関する研究
深層強化学習による自動運転車両の追い越し行動の実現に関する研究
 
PRML chapter7
PRML chapter7PRML chapter7
PRML chapter7
 
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
 
スパースモデリング、スパースコーディングとその数理(第11回WBA若手の会)
スパースモデリング、スパースコーディングとその数理(第11回WBA若手の会)スパースモデリング、スパースコーディングとその数理(第11回WBA若手の会)
スパースモデリング、スパースコーディングとその数理(第11回WBA若手の会)
 
[DL輪読会]“SimPLe”,“Improved Dynamics Model”,“PlaNet” 近年のVAEベース系列モデルの進展とそのモデルベース...
[DL輪読会]“SimPLe”,“Improved Dynamics Model”,“PlaNet” 近年のVAEベース系列モデルの進展とそのモデルベース...[DL輪読会]“SimPLe”,“Improved Dynamics Model”,“PlaNet” 近年のVAEベース系列モデルの進展とそのモデルベース...
[DL輪読会]“SimPLe”,“Improved Dynamics Model”,“PlaNet” 近年のVAEベース系列モデルの進展とそのモデルベース...
 
Deep Reinforcement Learning and Its Applications
Deep Reinforcement Learning and Its ApplicationsDeep Reinforcement Learning and Its Applications
Deep Reinforcement Learning and Its Applications
 
【DL輪読会】論文解説:Offline Reinforcement Learning as One Big Sequence Modeling Problem
【DL輪読会】論文解説:Offline Reinforcement Learning as One Big Sequence Modeling Problem【DL輪読会】論文解説:Offline Reinforcement Learning as One Big Sequence Modeling Problem
【DL輪読会】論文解説:Offline Reinforcement Learning as One Big Sequence Modeling Problem
 
[DL輪読会]Deep Dynamics Models for Learning Dexterous Manipulation
[DL輪読会]Deep Dynamics Models for Learning Dexterous Manipulation[DL輪読会]Deep Dynamics Models for Learning Dexterous Manipulation
[DL輪読会]Deep Dynamics Models for Learning Dexterous Manipulation
 
[DL輪読会]"CyCADA: Cycle-Consistent Adversarial Domain Adaptation"&"Learning Se...
 [DL輪読会]"CyCADA: Cycle-Consistent Adversarial Domain Adaptation"&"Learning Se... [DL輪読会]"CyCADA: Cycle-Consistent Adversarial Domain Adaptation"&"Learning Se...
[DL輪読会]"CyCADA: Cycle-Consistent Adversarial Domain Adaptation"&"Learning Se...
 
Optimization and particle swarm optimization (O & PSO)
Optimization and particle swarm optimization (O & PSO) Optimization and particle swarm optimization (O & PSO)
Optimization and particle swarm optimization (O & PSO)
 
はじめてのKrylov部分空間法
はじめてのKrylov部分空間法はじめてのKrylov部分空間法
はじめてのKrylov部分空間法
 
ベイズ推論とシミュレーション法の基礎
ベイズ推論とシミュレーション法の基礎ベイズ推論とシミュレーション法の基礎
ベイズ推論とシミュレーション法の基礎
 
Particle swarm optimization
Particle swarm optimizationParticle swarm optimization
Particle swarm optimization
 
Optimization tutorial
Optimization tutorialOptimization tutorial
Optimization tutorial
 
ADVANCED OPTIMIZATION TECHNIQUES META-HEURISTIC ALGORITHMS FOR ENGINEERING AP...
ADVANCED OPTIMIZATION TECHNIQUES META-HEURISTIC ALGORITHMS FOR ENGINEERING AP...ADVANCED OPTIMIZATION TECHNIQUES META-HEURISTIC ALGORITHMS FOR ENGINEERING AP...
ADVANCED OPTIMIZATION TECHNIQUES META-HEURISTIC ALGORITHMS FOR ENGINEERING AP...
 
Chapter9 2
Chapter9 2Chapter9 2
Chapter9 2
 
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recog...
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recog...Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recog...
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recog...
 
Gradient descent optimizer
Gradient descent optimizerGradient descent optimizer
Gradient descent optimizer
 

Similaire à Lecture 1 - Learning Dynamical Systems from Demonstrations

Introduction to Tutorial on Dynamical System-based Learning from Demonstratio...
Introduction to Tutorial on Dynamical System-based Learning from Demonstratio...Introduction to Tutorial on Dynamical System-based Learning from Demonstratio...
Introduction to Tutorial on Dynamical System-based Learning from Demonstratio...Nadia Barbara
 
[ICRA 2019] Introduction to Tutorial on Dynamical System-based Learning from ...
[ICRA 2019] Introduction to Tutorial on Dynamical System-based Learning from ...[ICRA 2019] Introduction to Tutorial on Dynamical System-based Learning from ...
[ICRA 2019] Introduction to Tutorial on Dynamical System-based Learning from ...Nadia Barbara
 
Lecture 3 - DS-based Impedance/Force Control
Lecture 3 - DS-based Impedance/Force ControlLecture 3 - DS-based Impedance/Force Control
Lecture 3 - DS-based Impedance/Force ControlNadia Barbara
 
[ICRA 2019] Lecture 4: Locally Active Globally Stable Dynamical Systems
[ICRA 2019] Lecture 4: Locally Active Globally Stable Dynamical Systems[ICRA 2019] Lecture 4: Locally Active Globally Stable Dynamical Systems
[ICRA 2019] Lecture 4: Locally Active Globally Stable Dynamical SystemsNadia Barbara
 
[ICRA 2019] Lecture 3: Impedance Control and Force Generation with DS
[ICRA 2019] Lecture 3: Impedance Control and Force Generation with DS[ICRA 2019] Lecture 3: Impedance Control and Force Generation with DS
[ICRA 2019] Lecture 3: Impedance Control and Force Generation with DSNadia Barbara
 
MDPSO_SDM_2012_Souma
MDPSO_SDM_2012_SoumaMDPSO_SDM_2012_Souma
MDPSO_SDM_2012_SoumaMDO_Lab
 
A MATLAB Toolbox for Piecewise-Affine Controller Synthesis
A MATLAB Toolbox for Piecewise-Affine Controller SynthesisA MATLAB Toolbox for Piecewise-Affine Controller Synthesis
A MATLAB Toolbox for Piecewise-Affine Controller SynthesisBehzad Samadi
 
Kane/DeAlbert dynamics for multibody system
Kane/DeAlbert dynamics for multibody system Kane/DeAlbert dynamics for multibody system
Kane/DeAlbert dynamics for multibody system Tadele Belay
 
Self-adaptation Driven by goals in SysML Models
Self-adaptation Driven by goals in SysML ModelsSelf-adaptation Driven by goals in SysML Models
Self-adaptation Driven by goals in SysML Modelsamalanda1
 
MVFI Meeting (January 14th, 2011)
MVFI Meeting (January 14th, 2011)MVFI Meeting (January 14th, 2011)
MVFI Meeting (January 14th, 2011)ivangomezconde
 
Requirements, Design and Data Repositories
Requirements, Design and Data RepositoriesRequirements, Design and Data Repositories
Requirements, Design and Data RepositoriesCS, NcState
 
Hybrid and reactive agent architecures
Hybrid and reactive agent architecuresHybrid and reactive agent architecures
Hybrid and reactive agent architecuresstevekahara
 

Similaire à Lecture 1 - Learning Dynamical Systems from Demonstrations (18)

Introduction to Tutorial on Dynamical System-based Learning from Demonstratio...
Introduction to Tutorial on Dynamical System-based Learning from Demonstratio...Introduction to Tutorial on Dynamical System-based Learning from Demonstratio...
Introduction to Tutorial on Dynamical System-based Learning from Demonstratio...
 
[ICRA 2019] Introduction to Tutorial on Dynamical System-based Learning from ...
[ICRA 2019] Introduction to Tutorial on Dynamical System-based Learning from ...[ICRA 2019] Introduction to Tutorial on Dynamical System-based Learning from ...
[ICRA 2019] Introduction to Tutorial on Dynamical System-based Learning from ...
 
Lecture 3 - DS-based Impedance/Force Control
Lecture 3 - DS-based Impedance/Force ControlLecture 3 - DS-based Impedance/Force Control
Lecture 3 - DS-based Impedance/Force Control
 
September 21, Modeling of Gradient-Based Controllers I
September 21, Modeling of Gradient-Based Controllers ISeptember 21, Modeling of Gradient-Based Controllers I
September 21, Modeling of Gradient-Based Controllers I
 
Mdpcg presentation
Mdpcg presentationMdpcg presentation
Mdpcg presentation
 
[ICRA 2019] Lecture 4: Locally Active Globally Stable Dynamical Systems
[ICRA 2019] Lecture 4: Locally Active Globally Stable Dynamical Systems[ICRA 2019] Lecture 4: Locally Active Globally Stable Dynamical Systems
[ICRA 2019] Lecture 4: Locally Active Globally Stable Dynamical Systems
 
Simulation Software Performances And Examples
Simulation Software Performances And ExamplesSimulation Software Performances And Examples
Simulation Software Performances And Examples
 
[ICRA 2019] Lecture 3: Impedance Control and Force Generation with DS
[ICRA 2019] Lecture 3: Impedance Control and Force Generation with DS[ICRA 2019] Lecture 3: Impedance Control and Force Generation with DS
[ICRA 2019] Lecture 3: Impedance Control and Force Generation with DS
 
MDPSO_SDM_2012_Souma
MDPSO_SDM_2012_SoumaMDPSO_SDM_2012_Souma
MDPSO_SDM_2012_Souma
 
A MATLAB Toolbox for Piecewise-Affine Controller Synthesis
A MATLAB Toolbox for Piecewise-Affine Controller SynthesisA MATLAB Toolbox for Piecewise-Affine Controller Synthesis
A MATLAB Toolbox for Piecewise-Affine Controller Synthesis
 
Making Robots Learn
Making Robots LearnMaking Robots Learn
Making Robots Learn
 
Kane/DeAlbert dynamics for multibody system
Kane/DeAlbert dynamics for multibody system Kane/DeAlbert dynamics for multibody system
Kane/DeAlbert dynamics for multibody system
 
Seminar2012 d
Seminar2012 dSeminar2012 d
Seminar2012 d
 
Deep Learning Summit (DLS01-2)
Deep Learning Summit (DLS01-2)Deep Learning Summit (DLS01-2)
Deep Learning Summit (DLS01-2)
 
Self-adaptation Driven by goals in SysML Models
Self-adaptation Driven by goals in SysML ModelsSelf-adaptation Driven by goals in SysML Models
Self-adaptation Driven by goals in SysML Models
 
MVFI Meeting (January 14th, 2011)
MVFI Meeting (January 14th, 2011)MVFI Meeting (January 14th, 2011)
MVFI Meeting (January 14th, 2011)
 
Requirements, Design and Data Repositories
Requirements, Design and Data RepositoriesRequirements, Design and Data Repositories
Requirements, Design and Data Repositories
 
Hybrid and reactive agent architecures
Hybrid and reactive agent architecuresHybrid and reactive agent architecures
Hybrid and reactive agent architecures
 

Dernier

GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...Lokesh Kothari
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformationAreesha Ahmad
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfSumit Kumar yadav
 
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxSCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxRizalinePalanog2
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000Sapana Sha
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfSumit Kumar yadav
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​kaibalyasahoo82800
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsSérgio Sacani
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfSumit Kumar yadav
 
Seismic Method Estimate velocity from seismic data.pptx
Seismic Method Estimate velocity from seismic  data.pptxSeismic Method Estimate velocity from seismic  data.pptx
Seismic Method Estimate velocity from seismic data.pptxAlMamun560346
 
GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)Areesha Ahmad
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...ssifa0344
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)Areesha Ahmad
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learninglevieagacer
 
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts ServiceJustdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Servicemonikaservice1
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bSérgio Sacani
 

Dernier (20)

GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdf
 
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxSCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdf
 
Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
CELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdfCELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdf
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Seismic Method Estimate velocity from seismic data.pptx
Seismic Method Estimate velocity from seismic  data.pptxSeismic Method Estimate velocity from seismic  data.pptx
Seismic Method Estimate velocity from seismic data.pptx
 
GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learning
 
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts ServiceJustdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
 
Clean In Place(CIP).pptx .
Clean In Place(CIP).pptx                 .Clean In Place(CIP).pptx                 .
Clean In Place(CIP).pptx .
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
 

Lecture 1 - Learning Dynamical Systems from Demonstrations

  • 1. Learning Dynamical Systems from Demonstrations 0 Organizers/Speakers: Nadia Figueroa, Sina Mirrazavi, Lukas Huber, Aude Billard
  • 2. Representing Robot Motions with an Autonomous Dynamical System (DS) Velocity Position Target Variables 1
  • 3. Representing Robot Motions with an Autonomous Dynamical System (DS) Velocity Position Target Variables Target 1x 2x x Lyapunov Theorem for Global Asymptotic Stability How to ensure convergence to the desired target? 2
  • 4. Global Asymptotic Stability of Autonomous Dynamical System (DS) Lyapunov Function ~ Energy-like Function Theorem A DS is globally asymptotically stable at iff there exists a Lyapunov candidate function that is radially unbounded; i.e. and satisfies the following conditions: V should be non-increasing along all trajectories. Lyapunov’s Theorem for Global Asymptotic Stability 3
  • 5. Lyapunov’s Theorem for Global Asymptotic Stability Level Sets of Lyapunov Function Theorem A DS is globally asymptotically stable at iff there exists a Lyapunov candidate function that is radially unbounded; i.e. and satisfies the following conditions: V should be non-increasing along all trajectories. Global Asymptotic Stability of Autonomous Dynamical System (DS) 4 Obtuse Angle
  • 6. Stability of a Linear Autonomous Dynamical System (DS) Quadratic Lyapunov Function (QLF) How to ensure is always negative? Enforce the eigenvalues to be negative! 5
  • 7. Stability of a Linear Autonomous Dynamical System (DS) Parametrized Quadratic Lyapunov Function (P-QLF) Enforce the eigenvalues to be negative! What if f(x) is non-linear? Stability not easy to define: local linearization; numerical estimation of stability; analytical solution in special cases. 6
  • 8. Representing Non-linear Motions as Mixtures of Linear DS 7 2-nd Linear DS 4-th Linear DS Activation/Mixing function for 2-nd DS Activation/Mixing function for 4-th DS How do we learn all of these parameters?
  • 9. 8 Learning Non-linear DS via Gaussian Mixture Regression Take a density based approach to modeling dynamical systems Given a set of demonstrations, learn the joint density via GMM 2D projection of a normal distribution    ~ ; ,p x N x  
  • 10. 9 Learning Non-linear DS via Gaussian Mixture Regression Through a slight change of variables To ensure Global Asymptotic Stability Khansari Zadeh, S. M. and Billard, A. (2011) IEEE Transactions on Robotics We estimate the Gaussian parameters via constraint- based optimization with stability constraints. Stability Constraints
  • 11. 10 Learning Non-linear DS via Gaussian Mixture Regression [1] Khansari Zadeh, S. M. and Billard, A. (2011) IEEE Transactions on Robotics Stable Estimator of Dynamical Systems (SEDS) Approach [1] Demonstrations Reproductions
  • 12. 11 SEDS in Action Khansari Zadeh, S. M. and Billard, A. (2011) IEEE Transactions on Robotics Demonstrations of Point-to-Point Motions Execution of Learned DS Motions
  • 13. 12 SEDS in Action [2] Figueroa, Pais and Billard. (2016) ACM/IEEE HRI Conference Demonstrations of Sequence of Point-to-Point Motions Execution of Sequence of Learned DS Motions Learn a point-to-point SEDS for each Phase + impedance/force profiles [2]
  • 14. 13 Limitations of SEDS Approach  Optimal number of K Gaussian components has to be set manually or ‘empirically’  Cannot handle highly non-linear motions: Why can’t we model these trajectories accurately?
  • 15. 14 These trajectories violate this condition QLF is too conservative. Acute Angles! Can we do better?
  • 16. 16 Acute Angles! Use Parametrized Quadratic Lyapunov Function (P-QLF)! These trajectories violate this condition QLF is too conservative. Acute Angles!
  • 17. 17 Learning Non-linear DS via GMMs with P-QLF We decouple the density estimation from the DS parameters Given a set of demonstrations, learn the GMM density on position variables only Solve a constrained optimization problem Stability Constraints Ensure Stability with P-QLF
  • 18. 18 Learning Non-linear DS via GMMs with P-QLF [3] Mirrazavi, BIllard. (2018) EPFL PhD Thesis. Linear Parameter Varying (LPV) Dynamical Systems (DS) Approach [2]
  • 19. 19 Outperforms SEDS in Reproduction Accuracy
  • 20. 20 Outperforms SEDS in Reproduction Accuracy
  • 21. 21 Limitations of LPV-DS Approach  Optimal number of K Gaussian components has to be set manually or ‘empirically’  Very sensitive to GMM fit: Good GMM fit
  • 22. 22 Limitations of LPV-DS Approach  Optimal number of K Gaussian components has to be set manually or ‘empirically’  Very sensitive to GMM fit: Bad GMM fit
  • 23. Other SEDS-based Extensions – beyond QLF Tau-SEDS Approach [4]: Based on Diffeomorphic Transformations And Complex Lyapunov Functions 23[4] Neumann, Steil (2015) Robotics and Autonomous Systems Step 1: Construct a Lyapunov Candidate Function Consistent with the Demonstrations Weighted Sum of Asymmetric Quadratic Functions (WSAQF) [5] [5] Khansari, Billard (2015) Robotics and Autonomous Systems
  • 24. Other SEDS-based Extensions – beyond QLF Tau-SEDS Approach [4]: Based on Diffeomorphic Transformations And Complex Lyapunov Functions 24 Step 2: Define a diffeomorphism where takes the form of a QLF Step 3: Transform the demonstrations via Step 4: Learn SEDS on transformed data. Step 1: Construct a Lyapunov Candidate Function Consistent with the Demonstrations [4] Neumann, Steil (2015) Robotics and Autonomous Systems [5] Khansari, Billard (2015) Robotics and Autonomous Systems
  • 25. Other SEDS-based Extensions – beyond QLF Tau-SEDS Approach [4]: Based on Diffeomorphic Transformations And Complex Lyapunov Functions 25 Step 2: Define a diffeomorphism where takes the form of a QLF Step 3: Transform the demonstrations via Step 4: Learn SEDS on transformed data. Step 5: Back-transform learn SEDS via Step 1: Construct a Lyapunov Candidate Function Consistent with the Demonstrations [4] Neumann, Steil (2015) Robotics and Autonomous Systems [5] Khansari, Billard (2015) Robotics and Autonomous Systems
  • 26. Other SEDS-based Extensions – beyond QLF 26 Contracting Dynamical Systems Primitives [5] [6] Ravichandar, Salehi, Dani (2017) CoRL Stability Constraints via Partial Contraction Theory
  • 27. Full List of Publications Mentioned in Lecture 27 [1] Khansari Zadeh, S. M. and Billard, A. (2011) Learning Stable Non-Linear Dynamical Systems with Gaussian Mixture Models. IEEE Transaction on Robotics, vol. 27, num 5, p. 943-957. [2] Figueroa, N., Pais, A. L. and Billard, A. (2016) Learning Complex Sequential Tasks from Demonstration: A Pizza Dough Rolling Case Study. In Proc. of the 2016 ACM/IEEE International Conference on Human-Robot Interaction. HRI Pioneers Workshop. [3] Mirrazavi Salehian, S. S. (2018) Compliant control of Uni/ Multi- robotic arms with dynamical systems. PhD Thesis. [4] K. Neumann and J. J. Steil. (2015) Learning robot motions with stable dynamical systems under diffeomorphic transformations. Robotics and Autonomous Systems, 70 (Supplement C):1 – 15 [5] Khansari Zadeh, S. M. and Billard, A. (2014) Learning Control Lyapunov Function to Ensure Stability of Dynamical System-based Robot Reaching Motions. Robotics and Autonomous Systems [6] H. Ravichandar, I. Salehi, and A. Dani. (2017) Learning partially contracting dynamical systems from demonstrations. In Proceedings of the 1st Annual Conference on Robot Learning, vol. 78 of Proceedings of Machine Learning Research, pp 369–378
  • 28. Exercise Session 1 28 Selection of number of Gaussians Selection of Objective Function
  • 29. Exercise Session 1 29 Selection of number of Gaussians Selection of Optimization Variant
  • 30. Exercise Session 1 30 Selection of Optimization Variant P is unknown, is estimated jointly with A’s. P is known, it is estimated a priori via [5] [5] Khansari, Billard (2015) Robotics and Autonomous Systems