inside a self driving uber
play

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

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


  1. Inside a Self-Driving Uber Matt Ranney March 6, 2018

  2. 1.3 million people die in car crashes every year.

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

  4. source: US National Highway Tra ffi c Safety Administration US only statistics for crash event causes

  5. source: US National Highway Tra ffi c Safety Administration US only statistics for crash event causes

  6. • Americans average 293 hours driving every year.

  7. • Americans average 293 hours driving every year. • There are over 1 Billion cars in the world, but they sit idle 96% of the time.

  8. • 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.

  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. • In many cities, up to 20% of the land is devoted to parking. Houston, TX Little Rock, AR Source: Old Urbanist and photoLith

  10. Self-driving cars will make our roads safer.

  11. Self-driving cars will give us our time and space back.

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

  13. Hardware

  14. Top mounted 360° Lidar

  15. Top mounted 360° Lidar Forward facing cameras

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

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

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

  19. Sensors Compute Vehicle

  20. Sensors Compute Vehicle Uber Rider Tablet App

  21. Software

  22. Rider Input

  23. Rider Input Navigation

  24. Rider Input Navigation

  25. Rider Input Navigation Sensors

  26. Rider Input Navigation Sensors Localization

  27. Rider Input Navigation Sensors Localization

  28. Rider Input Navigation Sensors Perception Localization

  29. Rider Input Navigation Sensors Perception Localization

  30. Rider Input Navigation Sensors Perception Prediction Localization

  31. Rider Input Navigation Sensors Perception Prediction Localization

  32. Rider Input Navigation Sensors Perception Prediction Planning Localization

  33. Rider Input Navigation Sensors Perception Prediction Planning Localization

  34. Rider Input Navigation Sensors Perception Prediction Planning Controls Localization

  35. Rider Input Navigation Sensors Perception Prediction Planning Controls Vehicle Localization

  36. Testing

  37. Online Testing with real vehicles

  38. Online Testing with real vehicles • Slow

  39. Online Testing with real vehicles • Slow • Expensive

  40. Online Testing with real vehicles • Slow • Expensive • Inconsistent

  41. Online Testing with real vehicles • Slow • Expensive • Inconsistent • Poor Coverage

  42. Online Testing with real vehicles • Slow • Expensive • Inconsistent • Poor Coverage • Absolutely Necessary

  43. O ffl ine Testing with simulation

  44. O ffl ine Testing with simulation • Fast

  45. O ffl ine Testing with simulation • Fast • Cheaper

  46. O ffl ine Testing with simulation • Fast • Cheaper • Consistent

  47. O ffl ine Testing with simulation • Fast • Cheaper • Consistent • Full Coverage

  48. O ffl ine Testing with simulation • Fast • Cheaper • Consistent • Full Coverage • Absolutely Necessary

  49. Rider Input Navigation Sensors Perception Prediction Planning Controls Vehicle Localization

  50. Logged Rider Input Navigation Logged Vehicle Perception Prediction Planning Controls Sensors Model Localization Vehicle Pose Log Sim

  51. Logged Rider Input Navigation Vehicle Game Perception Output Prediction Planning Controls Model Engine Vehicle Pose Virtual Sim

  52. Write New Software Update ML Models

  53. Write New Software Update ML Models Test with Simulation suite

Recommend


More recommend