AI and Autonomous Vehicles

1
AI and Autonomous Vehicles

• Daniel Landers
• COMP- 4640 Intelligent and Interactive Systems
• 3/10/2007

2
History of Autonomous Vehicles

• 1977 Tsukuba Mechanical Engineering
  LabAchieved speeds of 20 mph on a dedicated
  street, by tracking special white markers on the
  road.

3
History of Autonomous Vehicles

• 1980s Ernst Dickmanns at Bundeswehr
  Universitat MunchenA vision-guided Mercedes-Benz
  van achieved 60 mph on streets without any other
  traffic present.

4
History of Autonomous Vehicles

• 1995 - Ernst Dickmanns at Bundeswehr Universitat
  MunchenS-Class Mercedes-Benz achieved speeds of
  110 mph on a 1000 mile trip.
• Achieved 95 autonomous driving

5
History of Autonomous Vehicles

• 1995 CMU Navlab
• Achieved 98.2 autonomous driving on 3000 mile
  drive across the U.S.
• Throttle and brakes controlled by a human

6
Enter the Darpa Grand Challenge

• DARPA Defense Advanced Research Projects Agency
• The U.S. Congress allotted 1 Million Dollars to
  the winner of the 2004 challenge.
• Nobody won!
• In 2005, the prize money was upped to 2 million.

7
Its a hard problem!!!

• What is the Darpa Grand Challenge?
• Why they have a qualifier!

8
(No Transcript)
9
2005 Grand Challenge

• October 8, 2005
• Mojave Desert
• 132 Miles (212.4 km)
• 5 Autonomous Vehicles completed the course!
• Winner Stanley from Stanford University
• Finished in 6 hours and 54 minutes. Averaged 19
  mph on the course.

10
Stanley Stanford Racing Team
11
The AI Behind It

• An Autonomous Vehicle is an autonomous agent.
• Consists of
• Sensor Systems
• Actuator Systems
• Computation Systems

12
The AI Behind It (cont.)

• Sensors Sense the surrounding environment and
  report.
• Examples
• Vision
• Radar
• Laser
• Vehicle Sensors (Odometer, Fuel Gauge, Oil
  pressure, Engine Temperature)

13
The AI Behind It (cont.)

• Actuators Acting upon the environment.
• Examples
• Steering
• Gas / Throttle
• Brakes
• Vehicle Starting
• Lights
• Sirens

14
The AI Behind It (cont.)

• Computation The brains which process sensor
  data and apply the correct actuation to achieve
  the goal.
• Tasks
• Processing sensor input
• Path planning
• Actuator Manipulation

15
AI Case Study - Stanley

• Powered by seven Pentium M computers with battery
  power system.
• Sensors
• GPS
• Inertial Measurement Unit
• Wheel Speed Sensors
• Laser Range Finders
• Radar
• Stereo Camera Pair / Monocular Vision Systems
• Actuator Drive-by-wire system developed by
  Volkswagen (Steering, brake, and throttle
  actuators)

16
Stanley Navigating Video
17
(No Transcript)
18
Sample tracking visualization from on-board
computer
19
(No Transcript)
20
So, since Stanley did so well..

• Whats Next?

21
Whats Next?

• DARPA Urban Challenge
• November 3, 2007
• 60 miles
• Urban area course
• Must be completed in less than 6 hours
• Must obey all traffic regulations, negotiate with
  other traffic, and merge into traffic.

22
Urban Challenge Basic Rules

• Vehicle must be stock or have a documented safety
  record.
• Vehicle must obey the California state driving
  laws.
• Vehicle must be entirely autonomous, using only
  GPS and the information it detects with its
  sensors.
• DARPA will provide the route network 24 hours
  before the race starts.
• Vehicles will complete the route by driving
  between specified checkpoints.
• DARPA will provide a file detailing the order the
  checkpoints must be driven to 5 minutes before
  the race start.
• Vehicles may stop and stare for at most 10
  seconds.
• Vehicles must operate in rain and fog, with GPS
  blocked.
• Vehicles must avoid collision with vehicles and
  other objects such as carts, bicycles, traffic
  barrels, and objects in the environment such as
  utility poles.
• Vehicles must be able to operate in parking areas
  and perform U-turns as required by the situation.
  

23
The new challenge

• Other agents in the environment

24
References

• http//www.darpa.mil/grandchallenge/index.asp
• http//en.wikipedia.org/wiki/Darpa_grand_challenge
  
• http//cs.stanford.edu/group/roadrunner//old/techn
  ology.html
• http//www.pbs.org/wgbh/nova/darpa
• http//www.autonvs.com/technology.html