live in the car inside look into
play

LIVE IN THE CAR: INSIDE LOOK INTO AUTONOMOUS VEHICLE DRIVE MISSIONS - PowerPoint PPT Presentation

LIVE IN THE CAR: INSIDE LOOK INTO AUTONOMOUS VEHICLE DRIVE MISSIONS Neda Cvijetic 1 WHAT ARE DRIVE MISSIONS? DRIVE MISSIONS = PIECES OF AV SW FUNCTIONALITY THAT TEACH THE CAR TO DRIVE ITSELF 2 DRIVE MISSIONS: PERCEPTION 3 WHAT A HUMAN SEES


  1. LIVE IN THE CAR: INSIDE LOOK INTO AUTONOMOUS VEHICLE DRIVE MISSIONS Neda Cvijetic 1

  2. WHAT ARE DRIVE MISSIONS? DRIVE MISSIONS = PIECES OF AV SW FUNCTIONALITY THAT TEACH THE CAR TO DRIVE ITSELF 2

  3. DRIVE MISSIONS: PERCEPTION 3

  4. WHAT A HUMAN SEES 4

  5. WHAT THE AI CAR COMPUTER SEES One slide explanation of what DNNs are and how they work, highlighting relevance of matrix multiplication 5

  6. HOW A DEEP NEURAL NETWORK SEES Image “Audi A7” Image source: “Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks” ICML 2009 & Com m. ACM 2011. 6 Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Ng.

  7. OBSTACLE PERCEPTION 7

  8. PATH PERCEPTION 8

  9. 9

  10. EXAMPLE: INTERSECTION DETECTION AI-based Wait Conditions Detection 10

  11. EXAMPLE: INTERSECTION DETECTION AI-based Wait Conditions Detection 11

  12. WAITNET 12

  13. WAITNET 13

  14. DRIVE MISSIONS: LOCALIZATION + MAPPING 14

  15. 15

  16. 16

  17. DRIVE MISSIONS: PLANNING 17

  18. 18

  19. NVIDIA SAFETY FORCE FIELD https://www.nvidia.com/en-us/self-driving-cars/safety-force-field/ 19

  20. 20

  21. 21

  22. 22

  23. 23

  24. DRIVE MISSIONS: SIM + CONSTELLATION 24

  25. DRIVE MISSIONS IN DRIVE SIM Nightly battery of tests Reproducible results ( ex: Euro NCAP ) SAME weather SAME time of day SAME test drivers SAME test pedestrians Euro NCAP CCRs: Slower target vehicle Heyford Test Track, UK 25

  26. SIM = RAPID PROTOTYPING Validate functionality over 1,000s of conditions Dangerous or Expensive scenarios Permutations of scenarios Internationalization Different sensor configurations 26

  27. SIM = RAPID PROTOTYPING Validate functionality over 1,000s of conditions Dangerous or Expensive scenarios Permutations of scenarios Internationalization Different sensor configurations 27

  28. “ Autonomous vehicles need to be driven more than 11 billion miles to be 20% better than humans. With a fleet of 100 vehicles, 24 hours a day, 365 days a year, at 25 miles per hour, this would take 518 years. ” Rand Corporation, Driving to Safety 28

  29. NVIDIA DRIVE SIM AND CONSTELLATION AV VALIDATION SYSTEM Virtual Reality AV Simulator Same Architecture as DRIVE Computer Simulate Rare and Difficult Conditions, Recreate Scenarios, Run Regression Tests, Drive Billions of Virtual Miles 10,000 Constellations Drive 3B Miles per Year 29

  30. AUTONOMOUS VEHICLE SENSORS Diversity and Redundancy in Data 30

  31. DRIVE AGX XAVIER World’s First Autonomous Machine Processor Most Complex SOC Ever Made | 9 Billion Transistors, 350mm 2 , 12nFFN | ~8,000 Engineering Years Diversity of Engines Accelerate Entire AV Pipeline | Designed for ASIL-D AV 31

  32. NVIDIA DRIVE AGX PEGASUS 320 TOPS for AI Inferencing Memory Bandwidth >1 TB/s 400W Data Center in the Trunk 32

  33. DRIVE MISSIONS: CULTURE OF SAFETY 33

  34. A CULTURE OF SAFETY One slide explanation of what DNNs are and how they work, highlighting relevance of matrix multiplication 34

  35. A CULTURE OF SAFETY Commitment to Recognized Industry Standards ● Commitment to all recognized safety standards ● Commitment to cybersecurity ● Commitment to AI education 35

  36. 36

Recommend


More recommend