Title: Probabilistic Control of Human Robot Interaction: Experiments with a Robotic Assistant for Nursing Homes
1Probabilistic Control of Human Robot
InteractionExperiments with a Robotic
Assistant for Nursing Homes
Joelle Pineau Michael Montemerlo Martha Pollack
Nicholas Roy Sebastian Thrun Carnegie Mellon
University University of Michigan
2Introducing Pearl A mobile robotic assistant
for elderly people and nurses
ROLE
Reminding to eat, drink, take meds
cameras
Providing info (TV, weather)
LCD mouth
Monitoring Rx adherence safety
Calling for help in emergencies
microphone speakers
Supporting communication
touchscreen
Remote health services
handle bars
Providing physical assistance
carrying tray
Management support of ADLs
laser
Linking caregiver and resources
sonars
Moving things around
mobile base
3The Nursebot project in its early days
4Architecture
High-level controller
Cognitive support
Navigation
Communication
5Architecture
High-level controller
Cognitive support
Navigation
Communication
- Localization and map building
- (Burgard et al., 1999)
- People detection and tracking
- (Montemerlo et al., 2002)
6Architecture
High-level controller
Cognitive support
Navigation
Communication
- Autominder system
- (Pollack et al., 2002)
7Architecture
High-level controller
Cognitive support
Navigation
Communication
- Speech recognition Sphinx system
- (Ravishankar, 1996)
- Speech synthesis Festival system
- (Black et al., 1999)
8The role of the top-level controller
High-level controller
- Établir les priorités parmi les objectifs des
différents modules - Négocier entre plusieurs objectifs ayant des
coûts/gains variés
Cognitive support
Navigation
Communication
ACTION SELECTION - based on the trade-off
between - goals from different modules - goals
with varying costs / rewards - reducing
uncertainty versus accomplishing goals.
9Speech recognition with Sphinx
10Robot control under uncertainty
Belief State P(stweather-today)0.5 P(stappointm
ent-today )0.5
Speechtoday
State weather-today
USER
Action say-weather, update-appointment, clarif
y-query
11Robot control using Partially Observable Markov
Decision Processes (POMDPs)
Belief state
Observations Costs / Rewards
P(s1)
P(s2)
State
USER ENVIRONMENT WORLD
Actions
Problem Which action allows the robot to
maximize its reward?
12Methods to solve POMDPs
- Objective Find a policy, ?(b), which maximizes
reward.
POMDP
New methods?
Performance
AMDP
FIB
QMDP
UMDP
MDP
O(S2AT)
O(S2AO )
O(S2A)
O(S2AO)
O(S2AB)
T
Complexity
13New approach A hierarchy of POMDPs
- Idea Exploit domain knowledge to divide one
POMDP into many smaller ones. - Motivation Complexity of POMDP solving grows
exponentially with of actions. - Assumption We are given POMDP M
S,A,?,b,T,O,R and hierarchy H
subtask
Act
abstract action
ExamineHealth
Navigate
Move
ClarifyGoal
VerifyPulse
VerifyMeds
primitive action
North
South
East
West
14PolCA Planning with a hierarchy of POMDPs
- Step 1 Select the action set
-
Navigate
AMove N,S,E,W
Move
ClarifyGoal
South
East
West
North
ACTIONS North South East West ClarifyGoal VerifyPu
lse VerifyMeds
15PolCA Planning with a hierarchy of POMDPs
- Step 1 Select the action set
- Step 2 Minimize the state set
-
Navigate
AMove N,S,E,W SMove X,Y
Move
ClarifyGoal
South
East
West
North
ACTIONS North South East West ClarifyGoal VerifyPu
lse VerifyMeds
STATE FEATURES X-position Y-position X-goal Y-goal
HealthStatus
16PolCA Planning with a hierarchy of POMDPs
- Step 1 Select the action set
- Step 2 Minimize the state set
- Step 3 Choose parameters
-
Navigate
AMove N,S,E,W SMove X,Y
Move
ClarifyGoal
South
East
West
North
ACTIONS North South East West ClarifyGoal VerifyPu
lse VerifyMeds
STATE FEATURES X-position Y-position X-goal Y-goal
HealthStatus
PARAMETERS bh,Th,Oh,Rh
17PolCA Planning with a hierarchy of POMDPs
- Step 1 Select the action set
- Step 2 Minimize the state set
- Step 3 Choose parameters
- Step 4 Plan task h
-
Navigate
AMove N,S,E,W SMove X,Y
Move
ClarifyGoal
South
East
West
North
ACTIONS North South East West ClarifyGoal VerifyPu
lse VerifyMeds
STATE FEATURES X-position Y-position X-goal Y-goal
HealthStatus
PARAMETERS bh,Th,Oh,Rh
PLAN ?h
18PolCA in the Nursebot domain
- Goal A robot is deployed in a nursing home,
where it provides reminders to elderly users and
accompanies them to appointments. - Domain S512, A20, O19
- Hierarchy
19Sample scenario
20Results for dialogue system
POMDP policy MDP policy
0.18
0.1
0.1
21Summary
- We have developed a first prototype robot able to
serve as a mobile nursing assistant for elderly
people. - The top-level controller uses a hierarchical
variant of POMDPs to select actions. - This allows it to acquire necessary information
and successfully complete assigned tasks. - Probabilistic techniques have been found to be
very useful to flexibly model and track
individuals.
22The Nursebot team
CMU - Robotics Greg Armstrong Michael
Montemerlo Joelle Pineau Nicholas Roy Jamie
Schulte Sebastian Thrun CMU - HCI/Design Francin
e Gemperle Jennifer Goetz Sarah Kiesler Aaron
Powers
U. of Pittsburgh - Nursing Jacqueline
Dunbar-Jacobs Sandra Engberg Judith Matthews U.
of Pittsburgh - CS Don Chiarulli Colleen
McCarthy U. of Freiburg - CS Maren
Bennewitz Wolfram Burgard Dirk Schulz
U. of Michigan - CS Laura Brown Dirk
Colbry Cheryl Orosz Bart Peintner Martha
Pollack Sailesh Ramakrishnan Standard
Robotics Greg Baltus
For more details www.cs.cmu.edu/nursebot