Inside a Self-Driving Uber Matt Ranney March 6, 2018 1.3 million - - PowerPoint PPT Presentation

▶
inside a self driving uber
SMART_READER_LITE
LIVE PREVIEW

Inside a Self-Driving Uber Matt Ranney March 6, 2018 1.3 million - - PowerPoint PPT Presentation

Jan 06, 2023 298 likes •1.45k views

Inside a Self-Driving Uber Matt Ranney March 6, 2018 1.3 million people die in car crashes every year. source: https://crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/812499 source: US National Highway Tra ffi c Safety Administration US

slide-1
SLIDE 1

Inside a Self-Driving Uber

Matt Ranney March 6, 2018

slide-2
SLIDE 2
slide-3
SLIDE 3

1.3 million people die in car crashes every year.

slide-4
SLIDE 4

source: https://crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/812499

slide-5
SLIDE 5

source: US National Highway Traffic Safety Administration US only statistics for crash event causes

slide-6
SLIDE 6

source: US National Highway Traffic Safety Administration US only statistics for crash event causes

slide-7
SLIDE 7
slide-8
SLIDE 8
  • Americans average 293 hours driving every year.
slide-9
SLIDE 9
  • Americans average 293 hours driving every year.
  • There are over 1 Billion cars in the world, but they

sit idle 96% of the time.

slide-10
SLIDE 10
  • Americans average 293 hours driving every year.
  • There are over 1 Billion cars in the world, but they

sit idle 96% of the time.

  • In many cities, up to 20% of the land is devoted

to parking.

slide-11
SLIDE 11
  • Americans average 293 hours driving every year.
  • There are over 1 Billion cars in the world, but they

sit idle 96% of the time.

  • In many cities, up to 20% of the land is devoted

to parking.

Houston, TX Little Rock, AR

Source: Old Urbanist and photoLith

slide-12
SLIDE 12

Self-driving cars will make

  • ur roads safer.
slide-13
SLIDE 13

Self-driving cars will give us

  • ur time and space back.
slide-14
SLIDE 14
slide-15
SLIDE 15
slide-16
SLIDE 16
slide-17
SLIDE 17
slide-18
SLIDE 18
slide-19
SLIDE 19

Source: https://medium.com/@UberATG/the-future-of-trucking-b3d2ea0d2db9

slide-20
SLIDE 20
slide-21
SLIDE 21

Hardware

slide-22
SLIDE 22
slide-23
SLIDE 23

Top mounted 360° Lidar

slide-24
SLIDE 24

Top mounted 360° Lidar Forward facing cameras

slide-25
SLIDE 25

Side and rear facing cameras Top mounted 360° Lidar Forward facing cameras

slide-26
SLIDE 26

Side and rear facing cameras Top mounted 360° Lidar Forward facing cameras Radar Radar

slide-27
SLIDE 27

Compute, storage and cooling Side and rear facing cameras Top mounted 360° Lidar Forward facing cameras Radar Radar

slide-28
SLIDE 28
slide-29
SLIDE 29
slide-30
SLIDE 30
slide-31
SLIDE 31

Sensors Compute Vehicle

slide-32
SLIDE 32

Sensors Compute Vehicle Uber Rider App Tablet

slide-33
SLIDE 33

Software

slide-34
SLIDE 34
slide-35
SLIDE 35
slide-36
SLIDE 36

Rider Input

slide-37
SLIDE 37

Navigation Rider Input

slide-38
SLIDE 38
slide-39
SLIDE 39

Navigation Rider Input

slide-40
SLIDE 40

Sensors Navigation Rider Input

slide-41
SLIDE 41

Sensors Navigation Rider Input Localization

slide-42
SLIDE 42

Sensors Navigation Rider Input Localization

slide-43
SLIDE 43

Sensors Perception Navigation Rider Input Localization

slide-44
SLIDE 44
slide-45
SLIDE 45
slide-46
SLIDE 46
slide-47
SLIDE 47
slide-48
SLIDE 48
slide-49
SLIDE 49
slide-50
SLIDE 50
slide-51
SLIDE 51
slide-52
SLIDE 52

Sensors Perception Navigation Rider Input Localization

slide-53
SLIDE 53

Sensors Perception Prediction Navigation Rider Input Localization

slide-54
SLIDE 54
slide-55
SLIDE 55
slide-56
SLIDE 56

Sensors Perception Prediction Navigation Rider Input Localization

slide-57
SLIDE 57

Sensors Perception Prediction Planning Navigation Rider Input Localization

slide-58
SLIDE 58
slide-59
SLIDE 59
slide-60
SLIDE 60

Sensors Perception Prediction Planning Navigation Rider Input Localization

slide-61
SLIDE 61

Sensors Perception Prediction Planning Controls Navigation Rider Input Localization

slide-62
SLIDE 62

Sensors Vehicle Perception Prediction Planning Controls Navigation Rider Input Localization

slide-63
SLIDE 63

Testing

slide-64
SLIDE 64
slide-65
SLIDE 65
slide-66
SLIDE 66
slide-67
SLIDE 67
slide-68
SLIDE 68
slide-69
SLIDE 69
slide-70
SLIDE 70
slide-71
SLIDE 71

Online Testing with real vehicles

slide-72
SLIDE 72

Online Testing with real vehicles

  • Slow
slide-73
SLIDE 73

Online Testing with real vehicles

  • Slow
  • Expensive
slide-74
SLIDE 74

Online Testing with real vehicles

  • Slow
  • Expensive
  • Inconsistent
slide-75
SLIDE 75

Online Testing with real vehicles

  • Slow
  • Expensive
  • Inconsistent
  • Poor Coverage
slide-76
SLIDE 76

Online Testing with real vehicles

  • Slow
  • Expensive
  • Inconsistent
  • Poor Coverage
  • Absolutely Necessary
slide-77
SLIDE 77
slide-78
SLIDE 78

Offline Testing with simulation

slide-79
SLIDE 79

Offline Testing with simulation

  • Fast
slide-80
SLIDE 80

Offline Testing with simulation

  • Fast
  • Cheaper
slide-81
SLIDE 81

Offline Testing with simulation

  • Fast
  • Cheaper
  • Consistent
slide-82
SLIDE 82

Offline Testing with simulation

  • Fast
  • Cheaper
  • Consistent
  • Full Coverage
slide-83
SLIDE 83

Offline Testing with simulation

  • Fast
  • Cheaper
  • Consistent
  • Full Coverage
  • Absolutely Necessary
slide-84
SLIDE 84

Sensors Vehicle Perception Prediction Planning Controls Navigation Rider Input Localization

slide-85
SLIDE 85

Logged Sensors Vehicle Model Perception Prediction Planning Controls Navigation Logged Rider Input Localization

Vehicle Pose

Log Sim

slide-86
SLIDE 86
slide-87
SLIDE 87
slide-88
SLIDE 88

Vehicle Model Prediction Planning Controls Navigation Logged Rider Input

Vehicle Pose

Virtual Sim

Game Engine

Perception Output

slide-89
SLIDE 89
slide-90
SLIDE 90
slide-91
SLIDE 91
slide-92
SLIDE 92
slide-93
SLIDE 93
slide-94
SLIDE 94
slide-95
SLIDE 95
slide-96
SLIDE 96
slide-97
SLIDE 97
slide-98
SLIDE 98
slide-99
SLIDE 99

Write New Software Update ML Models

slide-100
SLIDE 100

Write New Software Update ML Models Test with Simulation suite

slide-101
SLIDE 101

Write New Software Update ML Models Test with Simulation suite Test on track

slide-102
SLIDE 102

Write New Software Update ML Models Test with Simulation suite Test on track Deploy to Test Fleet

slide-103
SLIDE 103

Write New Software Update ML Models Test with Simulation suite Test on track Deploy to Test Fleet Deploy to Full Fleet

slide-104
SLIDE 104

Extract Logged Data Write New Software Update ML Models Test with Simulation suite Test on track Deploy to Test Fleet Deploy to Full Fleet

slide-105
SLIDE 105

Extract Logged Data Identify Interesting Events Write New Software Update ML Models Test with Simulation suite Test on track Deploy to Test Fleet Deploy to Full Fleet

slide-106
SLIDE 106

Extract Logged Data Identify Interesting Events Write New Software Update ML Models Test with Simulation suite Test on track Deploy to Test Fleet Deploy to Full Fleet

slide-107
SLIDE 107
slide-108
SLIDE 108
slide-109
SLIDE 109

Please Help

slide-110
SLIDE 110
slide-111
SLIDE 111

Thanks

slide-112
SLIDE 112
slide-113
SLIDE 113

Sensors Vehicle Perception Prediction Planning Controls Navigation Rider Input Localization