Upload
others
View
1
Download
0
Embed Size (px)
Citation preview
Artificial Intelligence
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Driving Is Easy
Eating, phone calls, texting, sleeping
Drunk driving
Aggressive driving
Tuesday, November 10, 2009
Driving Is Hard!
Distance and velocity estimation
Physical dexterity
Piloting vs. navigating
Split-second reactions
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
To what extent and how can a multiagent intersection control mechanism take advantage of the capabilities of autonomous vehicles in order to
make automobile travel safer and faster?
The Question
Tuesday, November 10, 2009
DesiderataAutonomyLow communication complexitySensor model realismProtocol standardizationDeadlock/starvation avoidanceIncremental deployabilitySafetyEfficiency
Tuesday, November 10, 2009
MetricsMeasuring Efficiency
Delay: increased travel time due to intersection
Throughput: total vehicles/time/lane
Tuesday, November 10, 2009
Simulator
“aim3” http://code.google.com/p/aim3
~20K lines of Java
Discrete time (0.02 s)
Non-holonomic vehicle motion
Point-to-point/broadcast communication
Vehicle spawned using Poisson process
Tuesday, November 10, 2009
Vehicle-to-IntersectionDriver agents call ahead to reserve a region of space-time
Intersection manager approves or denies based on an intersection control policy
Vehicles may not enter the intersection without a reservation
Driver agents trust the intersection manager in the intersection
Tuesday, November 10, 2009
I’m arriving at time t...
Tuesday, November 10, 2009
Sounds good to me!
Tuesday, November 10, 2009
ProtocolREQ
UEST
source
_id
destin
ation_
id
vehicl
e_leng
th
vehicl
e_widt
h
maximu
m_acce
lerati
on
minimu
m_acce
lerati
on
minimu
m_velo
city
front_
wheel_
displa
cement
rear_w
heel_d
isplac
ement
max_st
eering
_angle
max_tu
rn_per
_secon
d
emerge
ncy
traver
sal_pr
oposal
s
arriva
l_time
arriva
l_velo
city
maximu
m_velo
city
CANCELsource_id
destination_idreservation_id
DONEsource_iddestination_id
AWAY
source_id
destination_idACZ
_REQUE
ST
source
_id
destin
ation_
id
start_
lane
target
_lane
vehicl
e_leng
th
ACZ_CA
NCEL
source
_id
destin
ation_
id
ticket
_numbe
r ACZ_ENTEREDsource_id
destination_id
ticket_number
ACZ_EXIT
source_i
d
destinat
ion_id
CONFIRMsource_iddestination_id
reservation_idarrival_timeearly_errorlate_error
arrival_lanedeparture_lane
arrival_velocity
acz_distanceaccelerations
REJECTsource_iddestination_id
next_communicationreason
EMERGENCY_STOPsource_iddestination_id
ACZ_CONFIRMsource_iddestination_idticket_numberstart_lanetarget_laneacz_distance
ACZ_REJECTsource_id
destination_idreason
Tuesday, November 10, 2009
The Important PointsProtocol
Set of messages and rules
Digitally signed
Agent implementations do not matter
Assume communication failure
Current mechanisms subsumed
Tuesday, November 10, 2009
The FCFS Policy
“First come, first served”
Primary policy
Grid of reservation tiles
Internal simulation of vehicles’ trajectories
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Reservation Tile
“Granularity”
Tuesday, November 10, 2009
Time t
Tuesday, November 10, 2009
Time t
Tuesday, November 10, 2009
FCFS Video
Tuesday, November 10, 2009
0
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
0 0.5 1 1.5 2 2.5
Dela
y (s
)
Traffic Level (vehicles/s)
Stop Sign
Traffic Light Minimum
FCFS
Optimal
Tuesday, November 10, 2009
Vehicle-to-Vehicle
Driver agents broadcast a claim
Define relations over claims:
✦ Conflict
✦ Priority
✦ Dominance
Permissibility
Tuesday, November 10, 2009
I’m arriving at time t...
Uh, I’m also arriving at time t...
I’m arriving at time t...
Time t for me too...
No, I’m arriving at time t...
Tuesday, November 10, 2009
1 2 3 4
source_id1
message_id13
ixn_id5
stopped_at_ixnfalse
arrival_lane1
departure_lane2
arrival_time128479
departure_time128523
source_id2
message_id6
ixn_id5
stopped_at_ixnfalse
arrival_lane1
departure_lane2
arrival_time128479
departure_time128613
source_id3
message_id10
ixn_id5
stopped_at_ixnfalse
arrival_lane1
departure_lane2
arrival_time128479
departure_time128497
source_id4
message_id4
ixn_id5
stopped_at_ixnfalse
arrival_lane1
departure_lane2
arrival_time128479
departure_time128564
Claim Claim Claim Claim
Tuesday, November 10, 2009
1 2 3 4
Claim Claim Claim Claim
Tuesday, November 10, 2009
1
32
4
“Dominance”
Tuesday, November 10, 2009
41 3
Permissible Nonpermissible
2
Tuesday, November 10, 2009
I’m arriving at time t...
Tuesday, November 10, 2009
I’m arriving at time t...
Tuesday, November 10, 2009
V2V Video
Tuesday, November 10, 2009
The BenefitsHuman Usability
Some people enjoy driving
Classic cars
Transition period
Concepts extend to cyclists, pedestrians
Tuesday, November 10, 2009
The FCFS-Signal PolicyAutonomous vehicles use protocolHuman-driven vehicles use signalsPolicy contains a signal modelUses state of relevant signal at arrival time:✦ Green: accept✦ Yellow: reject✦ Red: FCFSSet aside off-limits tiles during green phases
Tuesday, November 10, 2009
✔
Tuesday, November 10, 2009
✘
Tuesday, November 10, 2009
All-Lanes
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Single-Lane
Tuesday, November 10, 2009
Tuesday, November 10, 2009
0
10
20
30
40
50
60
0 0.5 1 1.5 2 2.5
Dela
y (s
)
Traffic Level (vehicles/s)
100% Human
10% Human
5% Human
1% Human
Fully Autonomous
Tuesday, November 10, 2009
Failure Mode Analysis
Enable collision detection
Trigger incidents, examine aftermath
Construct crash log
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Tuesday, November 10, 2009
10
20
30
40
50
60
70
80
90
100
0 10 20 30 40 50 60
Cars
Cra
shed
Time (s)
6 Lanes3 Lanes
Tuesday, November 10, 2009
Mitigating Catastrophe
Assume intersection manager can detect
Reaction:
✦ Refuse future reservations
✦ Emergency-Stop message
Oblivous vs. passive vs. active
What if vehicles do not receive?
Tuesday, November 10, 2009
Tuesday, November 10, 2009
1
1.5
2
2.5
3
3.5
0 2 4 6 8 10 12 14
Cars
Cra
shed
Time (s)
Passive20% receiving40% receiving60% receiving80% receiving
100% receiving
Tuesday, November 10, 2009
0
25
50
75
100
Oblivious20%
60%100% Receiving
Average Number Of Crashed Vehicles
6 Lanes 3 Lanes
Tuesday, November 10, 2009
0
1
2
3
4
Passive40%
80%
Average Number Of Crashed Vehicles
6 Lanes 3 Lanes
Tuesday, November 10, 2009
best case # of cars today: 1
worst case # of cars involved: 4.5
accidents due to driver error: ~96%
1 - (4.5 * 0.04) : 82%
Tuesday, November 10, 2009
What’s The Big Deal?Multiple Intersections
Protocol considerations
Downstream effects
Driver agent navigation
Upstream effects
Tuesday, November 10, 2009
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Distance
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
I’m arriving at time t...
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
✔
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
✔
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
Sounds good to me...
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
I’m arriving at time t′...
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
✘
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
Sorry! Can’t do that!
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
I’m away!
Tuesday, November 10, 2009
Admission Control Zone(ACZ)
ACZ Capacity
I’m away!
Tuesday, November 10, 2009
Multi-intersection Video
Tuesday, November 10, 2009
Other Results
Effects of multiple intersections
Emergency vehicles
On-the-fly policy switching
Learning policy selection
Tuesday, November 10, 2009
Intelligent VehiclesRelated Work
Object detection and tracking✦ Stereo far-IR/fusion (Mählisch et al. 2005)✦ Gray-valued video (Gepperth et al. 2005)Lane following✦ NN for Road Departure Warning (Kohl et al. 2006)✦ “No Hands Across America” (Pomerleau 1995)✦ Robust to lighting/road conditions (Watanabe and
Nishida 2005)✦ Unmarked roads (Ramström and Christensen 2005)Adaptive cruise control (Jaguar, Honda, BMW, Nissan, Toyota)
Tuesday, November 10, 2009
Traffic SignalsRelated Work
TRANSYT (Robertson 1969)
SCOOT (Hunt et al. 1981)
Cooperative traffic signals (Roozemond 1999)
Q-learning (Abdulhai et al. 2003)
Learning Classifier Systems (Bull et al. 2004)
MAS + game theory (Bazzan 2005)
History-based (Balan and Luke 2006)
Tuesday, November 10, 2009
Autonomous Vehicles at IntersectionsRelated Work
“Potential collision points”(Rasche and Naumann 1998)
Steering algorithms/collision avoidance(Reynolds 1999)
Platoons (Clement 2002, Hallé and Chaib-draa 2005)
Physical robots (Kolodko and Vlacic 2003)
Tuesday, November 10, 2009
Mixed SimulationFuture Directions
Tuesday, November 10, 2009
Proteus RobotsFuture Directions
Tuesday, November 10, 2009
Exploring AsynchronicityFuture Directions
Tuesday, November 10, 2009
Exploring AsynchronicityFuture Directions
Tuesday, November 10, 2009
??
?
?
??
?
?
?
?
?
?
?
Questions?
Tuesday, November 10, 2009