Title: Intentional Motion Online Learning and Prediction
1Intentional Motion On-line Learning and Prediction
- December 2005
- Dizan Vasquez, Thierry Fraichard, Olivier Aycard
and Christian Laugier - e-Motion, GRAVIR, CNRS
- INPGrenoble, INRIA, France
- firstname.lastname_at_inrialpes.fr
2Objective
- To predict intentional motion on the basis of
past and present observations. - How?Observe the environment in order to learn
typical behaviors, and then use them to predict.
3Related Works
- Trajectory Prototypes.KruseEtAl97,BennewitzEtAl0
2,VasquezFraichard04 - Learning using clustering
- Prediction using similaritymeasure.
- State Based Models.Zhu91,BuiEtAl02
- Learning using EM.
- Prediction using bayesianinference.
- Problems
- Unable to learn newbehaviors.
- Unable to adapt to achanging environment.
- Slow.
4Proposed Approach Plan Representation
- Learn and Predict HMM STRUCTURE PARAMETERS
GOAL IDENTIFICATION PREDICTION - An HMM is used to represent a planp( qt, qt-1,
ot ) p( qt-1 ) p( qt qt-1 ) p( ot qt )
qt-1
qt
qt1
ot-1
ot
ot1
- Extending to many plans p( qt, qt-1, ot, ? )
p( qt-1 ) p( ? ) p( qt qt-1, ?,) p( ot qt )
?
qt-1
qt
qt1
ot-1
ot
ot1
5Proposed Approach Learning
- Parameters to be learned
- Number of states N.
- Number of goals G.
- Allowed Transitions.
- Transition Probabilities p( qt qt-1, ?,).
Table Ag,i,j. - Observation Probabilities p( ot qt
).Gaussians Gi(µi,si) - Learning Process
Structure
Parameters
Prediction
Prediction
Prediction
O x1, y1 , x2, y2 , , xT, yT
Transition Learning
State Learning
State Learning
State Learning
Goal Learning
6Proposed Approach Learning (continues)
- State learning withGrowing Neural Gas
Fritzke95 - Place states where things happen.
- Advantages
- Fast (O(N) in time).
- N not fixed a priori.
- Incremental.
- Builds a planar graph
- Gaussian parameters
- µi wi.
- si average neighbors distance / 2.
7Proposed Approach Learning (continues)
- Goal Learning
- Another GNG is used.
- Only terminal observations are taken into
account. - Transition probabilities
- g Nearest goal to trajectory end.
- Counts are updated on a maximum
likelihood/Viterbi criterion.
8Proposed Approach Prediction
- Exact inference is possible in real time!
- Belief-state update O(GN2)? O(GN).
- Prediction modes
- Final goal. O(N)
- Intermediate states. O(GN2) ? O(GN).
9Experimental Results (continues)
10Conclusions and further work
- Our intentional motion approach
- Represent motion plans as HMM.
- Is able to learn and predict simultaneously.
- Proposes a novel use of GNG to determine the
number of HMMs, as well as their structure and
parameters. - Thanks to the chosen learning approach, exact
inference is linear with respect to the number of
states.
11Further Work
- Work has started on the parking lot
environment. - Problems detected with GNG for this kind of
environment. Switched to Grow When Required
MarslandEtAl02.
12 13Experimental Results
14Proposed Approach Prediction (continues)
15Objectives
- To predict intentional motion (ie motion
resulting from plan execution) on the basis of
past and present observations
?
?