AI and Self-Driving Cars Heechul Yun Autonomous Car - - PowerPoint PPT Presentation

▶
ai and self driving cars
SMART_READER_LITE
LIVE PREVIEW

AI and Self-Driving Cars Heechul Yun Autonomous Car - - PowerPoint PPT Presentation

Mar 31, 2024 141 likes •435 views

AI and Self-Driving Cars Heechul Yun Autonomous Car https://www.latimes.com/business/autos/la-fi-waymo-self-driving-california-20181030-story.html 2 Levels of Automation (SAE J3016) L1 Some cars today L2 Tesla L3 Uber

slide-1
SLIDE 1

AI and Self-Driving Cars

Heechul Yun

slide-2
SLIDE 2

Autonomous Car

2

https://www.latimes.com/business/autos/la-fi-waymo-self-driving-california-20181030-story.html

slide-3
SLIDE 3

Levels of Automation (SAE J3016)

  • L1

– Some cars today

  • L2

– Tesla

  • L3

– Uber

  • L4

– Waymo

  • L5

– None

3

(SAE, "Taxonomy and Definitions for Terms Related to On- Road Motor Vehicle Automated Driving Systems.")

slide-4
SLIDE 4

4

  • S. Kato, E. Takeuchi, Y. Ishiguro, Y. Ninomiya, K. Takeda, and T. Hamada. ``An Open Approach to Autonomous

Vehicles,'' IEEE Micro, Vol. 35, No. 6, pp. 60-69, 2015. Link

slide-5
SLIDE 5

Autoware

5

https://www.youtube.com/watch?v=zujGfJcZCpQ

slide-6
SLIDE 6

Autoware

  • Open-source software stack for self-driving

6

https://github.com/CPFL/Autoware

slide-7
SLIDE 7

Autoware

7

https://youtu.be/gq8El7-36z0?t=896

slide-8
SLIDE 8

Autoware

  • Limitations

– Require detailed 3D map – Require accurate localization (~cm) in the map – Heavily rely on expensive Lidar sensor

  • Cameras are supplementary

– Not the way human drives

8

slide-9
SLIDE 9

Bojarski et al., 2016, https://arxiv.org/abs/1604.07316

slide-10
SLIDE 10

Pixels to Actions

  • DNN based supervised learning
  • Imitating human driving behaviors
slide-11
SLIDE 11

How It Works?

  • Record data  train w/ data  apply in real world
  • Data = camera input, steering output
slide-12
SLIDE 12

http://selfdrivingcars.mit.edu/deeptesla/

slide-13
SLIDE 13

End-to-End Control

  • Deep learning based autonomous systems

Image: Prof. Levine, “Deep reinforcement learning via imitation learning”

slide-14
SLIDE 14

14

https://arxiv.org/abs/1901.08567

slide-15
SLIDE 15

This Week

  • AI & Deep Learning Basics
  • Deep Learning Based Self-Driving Cars
  • Challenges in AI and Real-Time
  • Papers

– End to End Learning for Self-Driving Cars, arXiv, 2016 (Kailani) – DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car, RTCSA, 2018 – An Open Approach to Autonomous Vehicles. MICRO, 2015 (optional) – Autoware on board: enabling autonomous vehicles with embedded systems, ICCPS, 2018 (optional)

slide-16
SLIDE 16

AI Resources

  • Lectures

– MIT 6.S094: Deep Learning for Self-Driving Cars – UC Berkeley CS188: Intro to AI – Andrej Karpathy's course on neural networks – Andrew Ng on Coursera – UC Berkeley CS294: Deep Reinforcement Learning – David Silver's course on reinforcement learning

  • Other useful links

– https://gym.openai.com/

slide-17
SLIDE 17

AI Resources

  • Research

– BADGR: An Autonomous Self-Supervised Learning- Based Navigation System

slide-18
SLIDE 18

DeepPicar

  • End-to-end deep learning: pixels to steering
  • Using identical DNN with NVIDIA’s DAVE-2

18

More self-driving videos: https://photos.app.goo.gl/q40QFieD5iI9yXU42

Michael G. Bechtel, Elise McEllhiney, Minje Kim, Heechul Yun. “DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car.” In RTCSA, 2018.

https://github.com/mbechtel2/DeepPicar-v2

slide-19
SLIDE 19

Project: Self-driving RC Car

  • Your tasks

– Build a car

  • We provide parts (can buy additional parts as needed)

– Implement vision based steering

  • We can provide baseline code

– Implement Lidar based emergency braking – Implement vision based traffic signal detection and stop/go – Demo and final report

19

slide-20
SLIDE 20

Possible Configuration

20

Raspberry Pi 4 (Linux) HiFive1 rev B Microcontroller Lidar Camera Intelligent controller (Vision based steering using DNN) Safety controller (Basic control + emergency breaking) Self-Driving Car

slide-21
SLIDE 21

DeepPicar Suite

  • Benchmark real-time apps for self-driving cars (on-going)

– Vision based steering control (DNN, 250K weights) – Voice recognition (DNN, 750K weights) – Traffic sign recognition (DNN, 1.4K weights) – Obstacle detection & emergency braking (Lidar)

  • General characteristics

– Data and compute intensive – Require efficient & performant computing platform

21

Voice recognition Obstacle detection Traffic sign recognition

slide-22
SLIDE 22

Embedded Platforms

  • HiFive1 (rev b) board

– RISC-V micro-controller – Limited resources/performance – “Bare-metal” programming in C

  • Directly access hardware w/o OS
  • Raspberry Pi 4

– Powerful quad-core ARM CPU – Run fully featured OS (Linux) – Standard PC-like programming environment

22

HiFive 1 rev B Raspberry Pi 4

slide-23
SLIDE 23

Sensors and Actuators

slide-24
SLIDE 24

EECS 388

http://www.ittc.ku.edu/~heechul/courses/eecs388/schedule.html

slide-25
SLIDE 25

RC Car Platforms

slide-26
SLIDE 26

Track

slide-27
SLIDE 27

Project Ideas

  • Reduce the size of the neural network so that

it can run on a less powerful computer (e.g., Raspberry pi zero, or hifive 1)

?

slide-28
SLIDE 28

Project Ideas

  • Learning to Drive in a Day

https://arxiv.org/pdf/1807.00412.pdf