1. The Darwinian Evolution of SmartDrivingCarsby
Alain L. Kornhauser, PhD Professor, Operations Research & Financial Engineering Director, Program in Transportation
Faculty Chair, PAVE (Princeton Autonomous Vehicle Engineering)
Princeton University
Presented at
ITS-NY
Twenty-first Annual Meeting
Saratoga Springs, NY
June 13, 2014

2. Outline “Safe Driving Vehicle”: 1939 -> Today +
What is a “Safe Driving Vehicle”
(aka DriverLessCars/SmartDrivingCars/Self-drivingCar/autonomousCars)
The 1st 75 years: (1939 -> 2014)
1939 -> DARPA Challenges
DARPA Challenges -> Today
“Safe”: Accident Mitigation v Accident Avoidance
The Opportunity for the Insurance Industry:
Trucks; Buses; Cars
Questions & Discussion

3. Scope of “Safe Driving Vehicle”
& Automation
Surface Transportation
Vehicle +
Running Surface
(aka roadway, guideway, railway)

4. Technology for Technology’s sake
The Evolution of Safe Driving Vehicle Technology to date

5. Scope of “Safe Driving Vehicles”
Tesla Car Transporter
Rio Tinto Automated Truck
Rio Tinto Automated Train
Tampa Airport 1st APM 1971
Automated Guided Vehicles
Copenhagen Metro
Elevator
Mercedes Intelligent Drive
Rivium >
Milton Keynes, UK
CityMobil2
Heathrow PodCar
Aichi, Japan, 2005 Expo
Volvo Truck

8. AHS: Automated Highway Systems: 1939 - 1997
“Waterloo” may well be the word “System”
Play video

9. APM: Automated People Mover: 1968 -
“Waterloo” limited to serve “Few to Few” demand

10. PRT: Personal Rapid Transit: 1968 -
Attempt to serve “Many to Many” but
“Waterloo” may well be the word “Personal” &
Exclusive Guideway?

11. V2V: Connected Vehicles: 1997 -
“Waterloo” may well be:
Zero value until market penetration is high

12. SDC: SmartDrivingCars: 2004 -
“Waterloo” may well be: Government & Bureaucracy
Real beauty is in its “autonomy”:
Benefits are derived by each equipped vehicle all by itself”
CityMobil2

13. Preliminary Statement of Policy Concerning Driverless Cars
What is a SmartDrivingCar?
Preliminary Statement of Policy Concerning Driverless Cars
Level 0 (No automation)
The human is in complete and sole control of safety-critical functions (brake, throttle, steering) at all times.
Level 1 (Function-specific automation)
The human has complete authority, but cedes limited control of certain functions to the vehicle in certain normal driving or crash imminent situations. Example: electronic stability control 
Level 2 (Combined function automation)
Automation of at least two control functions designed to work in harmony (e.g., adaptive cruise control and lane centering) in certain driving situations.
Enables hands-off-wheel and foot-off-pedal operation.
Driver still responsible for monitoring and safe operation and expected to be available at all times to resume control of the vehicle. Example: adaptive cruise control in conjunction with lane centering
Level 3 (Limited self-driving)
Vehicle controls all safety functions under certain traffic and environmental conditions.
Human can cede monitoring authority to vehicle, which must alert driver if conditions require transition to driver control.
Driver expected to be available for occasional control. Example: Google car
Level 4 (Full self-driving automation)
Vehicle controls all safety functions and monitors conditions for the entire trip.
The human provides destination or navigation input but is not expected to be available for control during the trip. Vehicle may operate while unoccupied. Responsibility for safe operation rests solely on the automated system
& Trucks
SmartDrivingCars

14. What is a SmartDrivingCar?
Preliminary Statement of Policy Concerning Driverless Cars
Level
“Less”
Value Proposition
Market Force
Societal Implications

15. What is a SmartDrivingCar?
Preliminary Statement of Policy Concerning Driverless Cars
Level
“Less”
Value Proposition
Market Force
Societal Implications
0 “55 Chevy”
Zero

16. What is a SmartDrivingCar?
Preliminary Statement of Policy Concerning Driverless Cars
Level
“Less”
Value Proposition
Market Force
Societal Implications
0 “55 Chevy”
Zero
1 “Cruise Control”
Infinitesimal
Some Comfort

17. What is a SmartDrivingCar?
Preliminary Statement of Policy Concerning Driverless Cars
Level
“Less”
Value Proposition
Market Force
Societal Implications
0 “55 Chevy”
Zero
1 “Cruise Control”
Infinitesimal
Some Comfort
2 “Collision Avoidance & Lane Centering”
Much Safety
(but Consumers don’t pay for Safety)
Needs help From “Flo & the Gecko” (Insurance incentivizes adoption)
“50%” fewer accidents; less severity-> 50% less insurance $ liability

18. What is a SmartDrivingCar?
Preliminary Statement of Policy Concerning Driverless Cars
Level
“Less”
Value Proposition
Market Force
Societal Implications
0 “55 Chevy”
Zero
1 “Cruise Control”
Infinitesimal
Some Comfort
2 “Collision Avoidance & Lane Centering”
Much Safety
(but Consumers don’t pay for Safety)
Needs help From “Flo & the Gecko” (Insurance incentivizes adoption)
“50%” fewer accidents; less severity-> 50% less insurance $ liability
3 “Texting Machine”
Some
Liberation (some of the time/places) ; more Safety
Consumers Pull, TravelTainment Industry Push
Increased car sales, many fewer insurance claims, slight + in VMT

19. What is a SmartDrivingCar?
Preliminary Statement of Policy Concerning Driverless Cars
Level
“Less”
Value Proposition
Market Force
Societal Implications
0 “55 Chevy”
Zero
1 “Cruise Control”
Infinitesimal
Some Comfort
2 “Collision Avoidance & Lane Centering”
Much Safety
(but Consumers don’t pay for Safety)
Needs help From “Flo & the Gecko” (Insurance incentivizes adoption)
“50%” fewer accidents; less severity-> 50% less insurance $ liability
3 “Texting Machine”
Some
Liberation (some of the time/places) ; more Safety
Consumers Pull, TravelTainment Industry Push
Increased car sales, many fewer insurance claims, slight + in VMT
4 “aTaxi “
Always
Chauffeured,
Buy Mobility “by the Drink” rather than “by the Bottle”
Profitable Business Opportunity for Utilities/Transit Companies
Personal Car becomes “Bling” not instrument of personal mobility, VMT ?; Comm. Design ? Energy, Congestion, Environment?

20. Preliminary Statement of Policy Concerning Driverless Cars
What the Levels Deliver:
Levels 1 -> 2: Increased Safety, Comfort & Convenience
Primarily an Insurance Discount Play
Levels 3: Increased Pleasure, Safety, Comfort & Convenience
An Enormous Consumer Play
Level 4 (Driverless Repositioning) : Pleasure, Mobility, Efficiency, Equity
Revolutionizes “Mass Transit” by Greatly Extending the Trips that can be “zero” cost of Labor.
(That was always the biggest “value” of PRT; zero labor cost for even zero-occupant trips)
A Corporate Utility/Fleet Play

22. Hmmm... this is enormously tragic because existing collision avoidance technology could have likely avoided this accident altogether even if Mr. Roper had not slept for 48 hours or was in complete compliance with all "hours of service regulations".  Even if Mr. Roper had not slept for 24 hours, tougher hours of service regulations would not have prevented this accident.  What would have prevented this accident would have been the availability of collision avoidance technology on this truck.  If Walmart somehow feels indisposed by this accident and wants to react constructively, Walmart should contribute to the advancement of collision avoidance technology and insist that all trucks moving their goods be equipped with such technology!  In fact, calling this an accident may well be a misnomer; maybe we should call it irresponsibility on Walmart’s part for not insisting that the trucks serving their stores have this technology.  The cost of this technology may well evolve to be more than offset by  the reduction in truck insurance expense. In other words, Walmart would not be indisposed and save money.  That doesn’t sound like an accident to me. It sounds like fiduciary (and societal) irresponsibility on the part of Walmart.  Of course, Walmart is not the only business that relies on long haul truckers to supply goods to its stores.  The Tracy Morgan collision should be a wake up call for businesses that rely on large trucks on US roads every day driven by drivers operating under pressure on deadlines.  Now that collision avoidance technology is available, Walmart and other business should insist that their logistics partners use trucks equipped with this technology.  They will save money in the long run and lives in the short and long runs.  Alain

23. Discussion!
Thank You

24. What About Buses?

25. Use Autonomous Collision Avoidance Technology to Address a BIG CURRENT Transit Problem

26. Good News! Travel by Bus is getting safer!

27. Good News! Injuries have been trending down!

28. Terrible News! Claims are going through the roof!

29. Casualty and Liability Claims are a Huge Drain on the Industry
For the 10 year period , more than $4.1 Billion was spent on casualty and liability claims
For many self-insured transit agencies these expenses are direct “out-of-pocket”

30. 2011 Nationwide Bus Casualty and Liability Expense
2011 Nationwide
Bus Casualty and Liability Expense
Source FTA NTD
Casualty and Liability Amount
Vehicle-related
$483,076,010.
Total Buses
59,871
Sub-Total Casualty and Liability Amount Per Bus
$8,069/Bus/Year

31. The Cost of Installing an Active Collision Avoidance System on a Bus Could be Recovered in as Little as One Year Through Reductions in Casualty and Liability Claims

32. Why New Jersey?
Observation: In 2 Years, NJ Transit will initiate a new Bus Replacement Cycle (That will extend for about 15 years)
Action Item:
Ensure that the Procurement Specifications include “Level 2” SmartDriving Technologies

33. Near-term Opportunity for a Substantive Extension of Autonomous Transit
Specific: General Mobility for Fort Monmouth Redevelopment
Currently: Decommissioned Ft. Monmouth is vacant .
Ft. Monmouth Economic Revitalization Authority (FMERA) is redeveloping the 3 sq. mile “city”
Focus is on attracting high-tech industry
The “Fort” needs a mobility system.
FMERA is receptive to incorporating an innovative mobility system
Because it is being redeveloped as a “new town” it can accommodate itself to be an ideal site for testing more advanced driverless systems.

34. Federal Transit Administration
The Initial Project:
Princeton University (with American Public Transit Association (APTA), Greater Cleveland Transit, and insurance pools from WA, CA, OH & VA)
Pending $5M Grant from
Federal Transit Administration
Focused on
Research, Certification and Commercialization of
SmartDriving Technology to Buses

35. Proposal Done: December 2, 2013: For next 6 months: Silence from FTA
In those 6 months approximately:
39 Fatalities
7,200 Injuries
$180M Claims
“Level 2 Collision Avoidance Technology”
Could cut those numbers in half
Why the delay in spending $5M to get the process started ???????

36. Discussion!
Thank You

37. What about Level 4 Implications on Energy, Congestion, Environment?
Assuming PLANNERS continue to PLAN as they do now.
How will people “get around”?
Assuming this new way of “getting around” offers different opportunities and constraints for PLANNERS to improve “Quality of Life”.
How will Zoning/Land-Use Change?

38. All about Ride-sharing
What about Level 4 Implications on Energy, Congestion, Environment? Assuming Planners Don’t Change
Land-Use hasn’t changed
Trip ends don’t change!
Assume Trip Distribution Doesn’t Change
Then it is only Mode Split.
Do I:
Walk?
Ride alone?
Ride with someone?
All about Ride-sharing

39. Kinds of RideSharing “AVO < 1” RideSharing “Organized” RideSharing
“Daddy, take me to school.” (Lots today)
“Organized” RideSharing
Corporate commuter carpools (Very few today)
“Tag-along” RideSharing
One person decides: “I’m going to the store. Wanna come along”. Other: “Sure”. (Lots today)
There exists a personal correlation between ride-sharers
“Casual” RideSharing
Chance meeting of a strange that wants to go in my direction at the time I want to go
“Slug”, “Hitch hiker”

40. aTaxis and RideSharing
“AVO < 1” RideSharing
Eliminate the “Empty Back-haul”; AVO Plus
“Organized” RideSharing
Diverted to aTaxis
“Tag-along” RideSharing
Only Primary trip maker modeled, “Tag-alongs” are assumed same after as before.
“Casual” RideSharing
This is the opportunity of aTaxis
How much spatial and temporal aggregation is required to create significant casual ride-sharing opportunities.

41. Spatial Aggregation By walking to a station/aTaxiStand
At what point does a walk distance makes the aTaxi trip unattractive relative to one’s personal car?
¼ mile ( 5 minute) max
Like using an Elevator!
Elevator

42. What about Level 4 Implications on Energy, Congestion, Environment
What about Level 4 Implications on Energy, Congestion, Environment? Assuming Planners Don’t Change
No Change in Today’s Walking, Bicycling and Rail trips
Today’s Automobile trips become aTaxi or aTaxi+Rail trips with hopefully LOTS of Ride-sharing opportunities

43. Pixelation of New Jersey
Zoomed-In Grid of Mercer
NJ State Grid

44. Pixelating the State with half-mile Pixels
xPixel = floor{ * (longitude )}
yPixel = floor{138.2 * (latitude – 38.9))

45. An aTaxiTrip An aTaxiTrip a PersonTrip
{oYpixel, oXpixel, oTime (Hr:Min:Sec) , }
An aTaxiTrip
{oYpixel, oXpixel, oTime (Hr:Min:Sec) ,dYpixel, dXpixel, Exected: dTime}
a PersonTrip
{oLat, oLon, oTime (Hr:Min:Sec) ,dLat, dLon, Exected: dTime} P1 D O O

46. Common Destination (CD)
CD=1p: Pixel -> Pixel (p->p) Ride-sharing P1 O
TripMiles = 2L
TripMiles = 3L
TripMiles = L

47. P1 O PersonMiles = 3L aTaxiMiles = L AVO = PersonMiles/aTaxiMiles = 3

48. Elevator Analogy of an aTaxi Stand Departure Delay: DD = 300 Seconds
Temporal Aggregation
Departure Delay: DD = 300 Seconds
Kornhauser
Obrien
Johnson
40 sec
Popkin
3:47
Henderson
Lin
1:34

49. Elevator Analogy of an aTaxi Stand
60 seconds later
Christie
Maddow
4:12
Henderson
Lin
Young
0:34
Samuels
4:50
Popkin
2:17

50. Spatial Aggregation By walking to a station/aTaxiStand
A what point does a walk distance makes the aTaxi trip unattractive relative to one’s personal car?
¼ mile ( 5 minute) max
By using the rail system for some trips
Trips with at least one trip-end within a short walk to a train station.
Trips to/from NYC or PHL

51. An aTaxiTrip a PersonTrip from NYC
{oYpixel, oXpixel, TrainArrivalTime, dYpixel, dXpixel, Exected: dTime}
a PersonTrip from NYC
(or PHL or any Pixel containing a Train station)
NYC
NJ Transit Rail Line to NYC, next Departure D O
Princeton Train Station
aTaxiTrip

52. Spatial Aggregation By walking to a station/aTaxiStand
A what point does a walk distance makes the aTaxi trip unattractive relative to one’s personal car?
¼ mile ( 5 minute) max
By using the rail system for some trips
Trips with at least one trip end within a short walk to a train station.
Trips to/from NYC or PHL
By sharing rides with others that are basically going in my direction
No trip has more than 20% circuity added to its trip time.

53. CD= 3p: Pixel ->3Pixels Ride-sharingO P2

54. CD= 3p: Pixel ->3Pixels Ride-sharingO

55. What about Level 4 Implications on Energy, Congestion, Environment?
I just need a Trip File for some Local
{Precise O, Precise oTime, Precise D}
For All Trips!
“Precise” Location: Within a Very Short Walk
~ Parking Space -> Front Door
(Properly account for accessibility differences: conventionalAuto v aTaxi)
“Precise” oTime : “to the second”
(Properly account for how long one must wait around to ride with someone else)

56. Trip Synthesizer (Activity-Based)
Project Overview
Trip Synthesizer (Activity-Based)
Motivation –
Publicly available TRAVEL Data do NOT contain:
Spatial precision
Where are people leaving from?
Where are people going?
Temporal precision
At what time are they travelling?
There is no data telling us when people are leaving their house, when they are coming back, where they are going in between

58. Synthesize from available data:
“every” NJ Traveler on a typical day NJ_Resident file
Containing appropriate demographic and spatial characteristics that reflect trip making
“every” trip that each Traveler is likely to make on a typical day. NJ_PersonTrip file
Containing appropriate spatial and temporal characteristics for each trip

59. Creating the NJ_Resident file
for “every” NJ Traveler on a typical day
NJ_Resident file
Start with Publically available data:

60. Bergen County @ Block Level
Population
Census Blocks
Median
Pop/ Block
Average
Pop/Block
BER
907,128
11,116 58
81.6

61. Assigning a Daily Activity (Trip) Tour to Each Person

62. NJ_PersonTrip file 9,054,849 records
All Trips
Home County
Trips
TripMiles
AverageTM #
Miles
ATL
936,585
27,723,931
29.6
BER
3,075,434
40,006,145
13.0
BUC
250,006
9,725,080
38.9
BUR
1,525,713
37,274,682
24.4
CAM
1,746,906
27,523,679
15.8
CAP
333,690
11,026,874
33.0
CUM
532,897
18,766,986
35.2
ESS
2,663,517
29,307,439
11.0
GLO
980,302
23,790,798
24.3
HUD
2,153,677
18,580,585
8.6
HUN
437,598
13,044,440
29.8
MER
1,248,183
22,410,297
18.0
MID
2,753,142
47,579,551
17.3
MON
2,144,477
50,862,651
23.7
MOR
1,677,161
33,746,360
20.1
NOR
12,534
900,434
71.8
NYC
215,915
4,131,764
19.1
OCE
1,964,014
63,174,466
32.2
PAS
1,704,184
22,641,201
13.3
PHL
46,468
1,367,405
29.4
ROC
81,740
2,163,311
26.5
SAL
225,725
8,239,593
36.5
SOM
1,099,927
21,799,647
19.8
SOU
34,493
2,468,016
71.6
SUS
508,674
16,572,792
32.6
UNI
1,824,093
21,860,031
12.0
WAR
371,169
13,012,489
35.1
WES
16,304
477,950
29.3
Total
32,862,668
590,178,597
19.3
 9,054,849 records
One for each person in NJ_Resident file
Specifying 32,862,668 Daily Person Trips
Each characterized by a precise
{oLat, oLon, oTime, dLat, dLon, Est_dTime}

63. NJ_PersonTrip file

65. http://orfe. princeton c

66. Results

67. Results

68. What about the whole country?

69. Public Schools in the US

70. Nation-Wide Businesses
Rank
State
Sales Volume
No. Businesses 1
California
$1,889
1,579,342 2
Texas
$2,115
999,331 3
Florida
$1,702
895,586 4
New York
$1,822
837,773 5
Pennsylvania
$2,134
550,678 9
New Jersey
$1,919
428,596 45
Washington DC
$1,317
49,488 47
Rhode Island
$1,814
46,503 48
North Dakota
$1,978
44,518 49
Delaware
$2,108
41,296 50
Vermont
$1,554
39,230 51
Wyoming
$1,679
35,881
13.6 Million Businesses {Name, address, Sales, #employees}
US Businesses: 13.6Million
US Employees: 240 Million (with Luke's 50M students, 12% Unemployment)
US Patrons: 330 Million (!!!)
US Sales Volume: 30Billion

71. US_PersonTrip file will have..
 308,745,538 records
One for each person in US_Resident file
Specifying 1,009,332,835 Daily Person Trips
Each characterized by a precise
{oLat, oLon, oTime, dLat, dLon, Est_dTime}
Will Perform Nationwide aTaxi AVO analysis
Results ????

76. Trip Files are Available If You want to Play

77. Discussion!
Thank You