demo_TPtrajGMM01.m 10 KB
Newer Older
Sylvain Calinon's avatar
Sylvain Calinon committed
1
function demo_TPtrajGMM01
2
% Task-parameterized model with trajectory-GMM encoding (GMM with dynamic features).
Sylvain Calinon's avatar
Sylvain Calinon committed
3
%
4 5 6 7
% Writing code takes time. Polishing it and making it available to others takes longer! 
% If some parts of the code were useful for your research of for a better understanding 
% of the algorithms, please reward the authors by citing the related publications, 
% and consider making your own research available in this way.
Sylvain Calinon's avatar
Sylvain Calinon committed
8 9 10
%
% @article{Calinon15,
%   author="Calinon, S.",
11 12 13
%   title="A Tutorial on Task-Parameterized Movement Learning and Retrieval",
%   journal="Intelligent Service Robotics",
%   year="2015"
Sylvain Calinon's avatar
Sylvain Calinon committed
14
% }
15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
% 
% Copyright (c) 2015 Idiap Research Institute, http://idiap.ch/
% Written by Sylvain Calinon, http://calinon.ch/
% 
% This file is part of PbDlib, http://www.idiap.ch/software/pbdlib/
% 
% PbDlib is free software: you can redistribute it and/or modify
% it under the terms of the GNU General Public License version 3 as
% published by the Free Software Foundation.
% 
% PbDlib is distributed in the hope that it will be useful,
% but WITHOUT ANY WARRANTY; without even the implied warranty of
% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
% GNU General Public License for more details.
% 
% You should have received a copy of the GNU General Public License
% along with PbDlib. If not, see <http://www.gnu.org/licenses/>.
32 33 34

addpath('./m_fcts/');

Sylvain Calinon's avatar
Sylvain Calinon committed
35

36 37 38 39 40 41
%% Parameters
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
model.nbStates = 3; %Number of Gaussians in the GMM
model.nbFrames = 2; %Number of candidate frames of reference
model.nbVarPos = 2; %Dimension of position data (here: x1,x2)
model.nbDeriv = 3; %Number of static&dynamic features (D=2 for [x,dx], D=3 for [x,dx,ddx], etc.)
Sylvain Calinon's avatar
Sylvain Calinon committed
42
model.nbVar = model.nbVarPos * model.nbDeriv; %Dimension of state vector
43
model.dt = 0.01; %Time step
Sylvain Calinon's avatar
Sylvain Calinon committed
44 45 46
nbData = 200; %Number of datapoints in a trajectory
nbRepros = 5; %Number of reproductions with new situations randomly generated

47 48 49 50 51 52 53

%% Load 3rd order tensor data
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
disp('Load 3rd order tensor data...');
% The MAT file contains a structure 's' with the multiple demonstrations. 's(n).Data' is a matrix data for
% sample n (with 's(n).nbData' datapoints). 's(n).p(m).b' and 's(n).p(m).A' contain the position and
% orientation of the m-th candidate coordinate system for this demonstration. 'Data' contains the observations
Sylvain Calinon's avatar
Sylvain Calinon committed
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
% in the different frames. It is a 3rd order tensor of dimension DC x P x N, with D=2 the dimension of a
% datapoint, C=2 the number of derivatives (incl. position), P=2 the number of candidate frames, and N=TM 
% the number of datapoints in a trajectory (T=200) multiplied by the number of demonstrations (M=5).
load('data/DataWithDeriv02.mat');

% %Convert position data to position+velocity data
% load('data/Data01.mat');
% %Create transformation matrix to compute derivatives
% D = (diag(ones(1,nbData-1),-1)-eye(nbData)) / model.dt;
% D(end,end) = 0;
% %Create 3rd order tensor data and task parameters
% Data = zeros(model.nbVar, model.nbFrames, nbSamples*nbData);
% for n=1:nbSamples
% 	s(n).Data = zeros(model.nbVar,model.nbFrames,nbData);
% 	s(n).Data0 = s(n).Data0(2:end,:); %Remove time
% 	DataTmp = s(n).Data0;
% 	for k=1:model.nbDeriv-1
% 		DataTmp = [DataTmp; s(n).Data0*D^k]; %Compute derivatives
% 	end
% 	for m=1:model.nbFrames
% 		s(n).p(m).b = [s(n).p(m).b; zeros((model.nbDeriv-1)*model.nbVarPos,1)];
% 		s(n).p(m).A = kron(eye(model.nbDeriv), s(n).p(m).A);
% 		s(n).Data(:,m,:) = s(n).p(m).A \ (DataTmp - repmat(s(n).p(m).b, 1, nbData));
% 		Data(:,m,(n-1)*nbData+1:n*nbData) = s(n).Data(:,m,:);
% 	end
% end
% %Save new dataset including derivatives
% save('data/DataWithDeriv02.mat', 'Data','s','nbSamples');
82 83

%Construct PHI operator (big sparse matrix)
Sylvain Calinon's avatar
Sylvain Calinon committed
84
[PHI,PHI1] = constructPHI(model, nbData, nbSamples); 
85 86 87 88


%% TP-GMM learning
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Sylvain Calinon's avatar
Sylvain Calinon committed
89
fprintf('Parameters estimation of TP-GMM with EM...');
90
%model = init_tensorGMM_timeBased(Data, model); %Initialization
Sylvain Calinon's avatar
Sylvain Calinon committed
91 92 93 94 95 96 97 98 99 100 101 102 103 104 105
%model = init_tensorGMM_kmeans(Data, model); %Initialization

%Initialization based on position data
model0 = init_tensorGMM_kmeans(Data(1:model.nbVarPos,:,:), model);
[~,~,GAMMA2] = EM_tensorGMM(Data(1:model.nbVarPos,:,:), model0);
model.Priors = model0.Priors;
for i=1:model.nbStates
	for m=1:model.nbFrames
		DataTmp = squeeze(Data(:,m,:));
		model.Mu(:,m,i) = DataTmp * GAMMA2(i,:)';
		DataTmp = DataTmp - repmat(model.Mu(:,m,i),1,nbData*nbSamples);
		model.Sigma(:,:,m,i) = DataTmp * diag(GAMMA2(i,:)) * DataTmp';
	end
end

106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125
model = EM_tensorGMM(Data, model);


%% Reproduction for the task parameters used to train the model
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
disp('Reproductions...');
for n=1:nbSamples
	%Products of linearly transformed Gaussians
	for i=1:model.nbStates
		SigmaTmp = zeros(model.nbVar);
		MuTmp = zeros(model.nbVar,1);
		for m=1:model.nbFrames
			MuP = s(n).p(m).A * model.Mu(:,m,i) + s(n).p(m).b;
			SigmaP = s(n).p(m).A * model.Sigma(:,:,m,i) * s(n).p(m).A';
			SigmaTmp = SigmaTmp + inv(SigmaP);
			MuTmp = MuTmp + SigmaP\MuP;
		end
		r(n).Sigma(:,:,i) = inv(SigmaTmp);
		r(n).Mu(:,i) = r(n).Sigma(:,:,i) * MuTmp;
	end
Sylvain Calinon's avatar
Sylvain Calinon committed
126 127 128 129 130
	%Create single Gaussian N(MuQ,SigmaQ) based on state sequence q, see Eq. (27)
	[~,r(n).q] = max(model.Pix(:,(n-1)*nbData+1:n*nbData),[],1); %works also for nbStates=1
	r(n).MuQ = reshape(r(n).Mu(:,r(n).q), model.nbVarPos*model.nbDeriv*nbData, 1);
	r(n).SigmaQ = zeros(model.nbVarPos*model.nbDeriv*nbData);
	for t=1:nbData
131 132 133
		id1 = (t-1)*model.nbVarPos*model.nbDeriv+1:t*model.nbVarPos*model.nbDeriv;
		r(n).SigmaQ(id1,id1) = r(n).Sigma(:,:,r(n).q(t));
	end
Sylvain Calinon's avatar
Sylvain Calinon committed
134
	%Retrieval of data with trajectory GMM, see Eq. (30)
135 136 137
	PHIinvSigmaQ = PHI1'/r(n).SigmaQ;
	Rq = PHIinvSigmaQ * PHI1;
	rq = PHIinvSigmaQ * r(n).MuQ;
Sylvain Calinon's avatar
Sylvain Calinon committed
138
	r(n).Data = reshape(Rq\rq, model.nbVarPos, nbData); %Reshape data for plotting
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165
end


%% Reproduction for new task parameters
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
disp('New reproductions...');
for n=1:nbRepros
	for m=1:model.nbFrames
		%Random generation of new task parameters
		id=ceil(rand(2,1)*nbSamples);
		w=rand(2); w=w/sum(w);
		rnew(n).p(m).b = s(id(1)).p(m).b * w(1) + s(id(2)).p(m).b * w(2);
		rnew(n).p(m).A = s(id(1)).p(m).A * w(1) + s(id(2)).p(m).A * w(2);
	end
	%GMM products
	for i=1:model.nbStates
		SigmaTmp = zeros(model.nbVar);
		MuTmp = zeros(model.nbVar,1);
		for m=1:model.nbFrames
			MuP = rnew(n).p(m).A * model.Mu(:,m,i) + rnew(n).p(m).b;
			SigmaP = rnew(n).p(m).A * model.Sigma(:,:,m,i) * rnew(n).p(m).A';
			SigmaTmp = SigmaTmp + inv(SigmaP);
			MuTmp = MuTmp + SigmaP\MuP;
		end
		rnew(n).Sigma(:,:,i) = inv(SigmaTmp);
		rnew(n).Mu(:,i) = rnew(n).Sigma(:,:,i) * MuTmp;
	end
Sylvain Calinon's avatar
Sylvain Calinon committed
166 167 168 169 170
	%Create single Gaussian N(MuQ,SigmaQ) based on state sequence q, see Eq. (27)
	[~,rnew(n).q] = max(model.Pix(:,1:nbData),[],1); %works also for nbStates=1
	rnew(n).MuQ = reshape(rnew(n).Mu(:,rnew(n).q), model.nbVarPos*model.nbDeriv*nbData, 1);
	rnew(n).SigmaQ = zeros(model.nbVarPos*model.nbDeriv*nbData);
	for t=1:nbData
171 172 173
		id1 = (t-1)*model.nbVarPos*model.nbDeriv+1:t*model.nbVarPos*model.nbDeriv;
		rnew(n).SigmaQ(id1,id1) = rnew(n).Sigma(:,:,rnew(n).q(t));
	end
Sylvain Calinon's avatar
Sylvain Calinon committed
174
	%Retrieval of data with trajectory GMM, see Eq. (30)
175 176 177
	PHIinvSigmaQ = PHI1'/rnew(n).SigmaQ;
	Rq = PHIinvSigmaQ * PHI1;
	rq = PHIinvSigmaQ * rnew(n).MuQ;
Sylvain Calinon's avatar
Sylvain Calinon committed
178
	rnew(n).Data = reshape(Rq\rq, model.nbVarPos, nbData); %Reshape data for plotting
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199
end


%% Plots
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
figure('position',[20,50,1300,500]);
xx = round(linspace(1,64,nbSamples));
clrmap = colormap('jet');
clrmap = min(clrmap(xx,:),.95);
limAxes = [-1.2 0.8 -1.1 0.9];
colPegs = [[.9,.5,.9];[.5,.9,.5]];

%DEMOS
subplot(1,3,1); hold on; box on; title('Demonstrations');
for n=1:nbSamples
	%Plot frames
	for m=1:model.nbFrames
		plot([s(n).p(m).b(1) s(n).p(m).b(1)+s(n).p(m).A(1,2)], [s(n).p(m).b(2) s(n).p(m).b(2)+s(n).p(m).A(2,2)], '-','linewidth',6,'color',colPegs(m,:));
		plot(s(n).p(m).b(1), s(n).p(m).b(2),'.','markersize',30,'color',colPegs(m,:)-[.05,.05,.05]);
	end
	%Plot trajectories
Sylvain Calinon's avatar
Sylvain Calinon committed
200 201
	plot(s(n).Data0(1,1), s(n).Data0(2,1),'.','markersize',12,'color',clrmap(n,:));
	plot(s(n).Data0(1,:), s(n).Data0(2,:),'-','linewidth',1.5,'color',clrmap(n,:));
202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
end
axis(limAxes); axis square; set(gca,'xtick',[],'ytick',[]);

%REPROS
subplot(1,3,2); hold on; box on; title('Reproductions');
for n=1:nbSamples
	%Plot frames
	for m=1:model.nbFrames
		plot([s(n).p(m).b(1) s(n).p(m).b(1)+s(n).p(m).A(1,2)], [s(n).p(m).b(2) s(n).p(m).b(2)+s(n).p(m).A(2,2)], '-','linewidth',6,'color',colPegs(m,:));
		plot(s(n).p(m).b(1), s(n).p(m).b(2),'.','markersize',30,'color',colPegs(m,:)-[.05,.05,.05]);
	end
end
for n=1:nbSamples
	%Plot trajectories
	plot(r(n).Data(1,1), r(n).Data(2,1),'.','markersize',12,'color',clrmap(n,:));
	plot(r(n).Data(1,:), r(n).Data(2,:),'-','linewidth',1.5,'color',clrmap(n,:));
end
for n=1:nbSamples
	%Plot Gaussians
Sylvain Calinon's avatar
Sylvain Calinon committed
221
	plotGMM(r(n).Mu(1:2,:,1), r(n).Sigma(1:2,1:2,:,1), [.5 .5 .5], .4);
222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
end
axis(limAxes); axis square; set(gca,'xtick',[],'ytick',[]);

%NEW REPROS
subplot(1,3,3); hold on; box on; title('New reproductions');
for n=1:nbRepros
	%Plot frames
	for m=1:model.nbFrames
		plot([rnew(n).p(m).b(1) rnew(n).p(m).b(1)+rnew(n).p(m).A(1,2)], [rnew(n).p(m).b(2) rnew(n).p(m).b(2)+rnew(n).p(m).A(2,2)], '-','linewidth',6,'color',colPegs(m,:));
		plot(rnew(n).p(m).b(1), rnew(n).p(m).b(2), '.','markersize',30,'color',colPegs(m,:)-[.05,.05,.05]);
	end
end
for n=1:nbRepros
	%Plot trajectories
	plot(rnew(n).Data(1,1), rnew(n).Data(2,1),'.','markersize',12,'color',[.2 .2 .2]);
	plot(rnew(n).Data(1,:), rnew(n).Data(2,:),'-','linewidth',1.5,'color',[.2 .2 .2]);
end
for n=1:nbRepros
	%Plot Gaussians
Sylvain Calinon's avatar
Sylvain Calinon committed
241
	plotGMM(rnew(n).Mu(1:2,:,1), rnew(n).Sigma(1:2,1:2,:,1), [.5 .5 .5], .4);
242 243 244
end
axis(limAxes); axis square; set(gca,'xtick',[],'ytick',[]);

Sylvain Calinon's avatar
Sylvain Calinon committed
245
%print('-dpng','graphs/demo_TPtrajGMM01.png');
246 247 248 249
%pause;
%close all;