1. An autonomous ground vehicle is a vehicle that navigates and drives entirely on its own with no human driver and no remote control. Through the use of various sensors and positioning systems, the vehicle determines all the characteristics of its environment required to enable it to carry out the task it has been assigned.

5. The Stanford Vehicle (nicknamed "Stanley") is based on a stock, Diesel-powered Volkswagen Touareg R5, modified with full body skid plates and a reinforced front bumper. Stanley is actuated via a drive- by-wire system developed by Volkswagen of America's Electronic Research Lab. All processing takes place on seven Pentium M computers, powered by a battery-backed, electronically-controlled power system. The vehicle incorporates measurements from GPS, a 6DOF inertial measurement unit, and wheel speed for pose estimation. While the vehicle is in motion, the environment is perceived through four laser range finders, a radar system, a stereo camera pair, and a monocular vision system. All sensors acquire environment data at rates between 10 and 100 Hertz. Map and pose information are incorporated at 10 Hz, enabling Stanley to avoid collisions with obstacles in real-time while advancing along the 2005 DARPA Grand Challenge route. The development of Stanley began in July 2004.

6. 1. GPS The rooftop GPS antenna receives data that has actually traveled twice into space - once to receive an initial position that is accurate up to a meter, and a second time to make corrections. The final reading is accurate up to 1 centimeter.

7.  The receiver of a GPS system gets signals from 3 or more GPS satellites and through knowing the position of and distance to at least 3 satellites, it can calculate its position through trilateration. Which is basically finding the position of something through the geometry of triangles. There are chances for error to be introduced at every step of the process.  31 Satellites in orbit at the moment.

8.  Ionospheric Effects +- 5 meters  Ephemeris Errors +- 2.5 meters  Satellite Clock Errors +- 2 meters  Multipath Distortion +-1 meter  Tropospheric Effects +-.5 meter  Numerical Errors+- 1 meter

9.  Carrier Phase-Enhancement  Relative Kinematic Positioning  More modern satellites

10. LIDAR scans the terrain 30 meters ahead and to either side of the grill five times a second. The data is used to build a map of the road

11.  (Light Detection and Ranging)  Like radar, but uses light instead of radio waves  Higher Resolution than radar  Laser range finder a type of LIDAR  Components – laser, scanner and optics, receiver and receiver electronics, positioning and navigation systems  30 meters ahead? 60 milesph ~ 29.333 meters per second  1 second to react to LIDAR data alone

12.  5 LIDAR Units in Stanley  LIDAR used in adaptive cruise control  LIDAR guns for traffic speed measurement  Used for atmospheric measurements related to weather patterns, forestry, oceanography, earthquake monitoring, glacier movement, hurricane monitoring, 3-D imaging

13. The video camera scans the road beyond the LIDAR's range and pipes the data back to the computer. If the lasers have identified drivable ground, software looks for the same characteristics in the video data, extending Stanley's vision to 80 meters and permitting safe acceleration.

14. Video Cameras, aka Remote Sensing  Another “related to GIS” technology  Each pixel a camera receives is simply a shade of color  On-the-fly road, vehicle, and obstacle recognition  Processing power  Better algorithms  Reliance on success of this process

15. Every car on the road has a camera?  Maybe the camera just uses and forgets data it needs…  …maybe it doesn’t  Privacy issues  Does it matter? Is it a good / bad thing?  Will it help with accidents? “It wasn’t my fault officer, the car was driving”

16. To contend with signals blocked by, say, a tunnel or mountain, a photo sensor in the wheel well monitors a pattern imprinted on Stanley's wheels. The data is used to determine how far Stanley has moved since the blackout. The onboard computer can then track the vehicle's position based on its last known GPS location.

17. Dead Reckoning  What if the GIS and GPS was so accurate that all you needed was a GPS coordinate after each block / mile / 50 miles?  Accurate enough to truly be a backup system for GPS? Could all of rush hour traffic use it at the same time?

18. Stanley prepares to pass a robotic Hummer on a 3D terrain map plotted by a light detection and LIDAR. 1. The Mapper program interprets the map as a grid. 2. White cells mean driveable road; red cells (an obstacle), and gray cells (unknown conditions). The Planner then plots safe route options, marked by green lines around the obstacle. 3. A video camera samples Mapper-defined “good” road (below blue line) And searches for similar-looking terrain ahead. Example:

19.  Highly accurate (< 1 cm of error) street maps  Streets cannot just be centerlines, but become polygons of varying shapes and sizes  If no accurate map exists, build one from LIDAR, GPS data  GIS is the “last line of defense” against running into something, as you are probably getting more time critical data from LIDAR, GPS, video camera  GIS used mostly for route calculation, while LIDAR and to a lesser extent GPS used for navigating what is happening on the road  Tied into GPS, LIDAR, remote sensing systems

21.  Lots of GPS traffic and reliance on GPS systems, what happens when GPS fails during rush hour?  Urban environments can cause GPS interference, as well as confuse LIDAR  If you get in a wreck / kill somebody while the car is driving, whose fault is it? Do you need insurance company approval, designated lanes, totally mixed car populations?  More accurate GPS, GIS, LIDAR More GPS relayers on the ground? Road system upgrades? Special lane paint? Reflectors?  Better algorithms for tying all systems together

22.  Unified Standards (ok, it’s a little early)  Are people ready?  Cost LIDAR units, GPS receivers, an actual computer in each car? Municipal costs of additional receivers, repeaters, road paint, reflectors, etc More and better satellites

23. 1. Road Condition Reporting When a car using BMW's hazard system slips on ice, its sensors activate traction control. Meantime, wireless technology alerts other cars in the area to the hazard. 2. Adaptive Cruise Control Luxury cars made by Audi, BMW, Infiniti, and others now use radar-guided cruise control to keep pace with the car ahead. 3. Omnidirectional Collision System GM has built an inexpensive collision detection system that allows GPS-equipped cars to identify each other and communicate wirelessly.

24. 4. Lane-Departure Prevention Nissan has a prototype that uses cameras and software to detect white lines and reflective markers. If the system determines the vehicle is drifting, it will steer the car back into the proper lane. 5. Auto Parallel Park Toyota has a technology that uses a camera to identify a curbside parking space and turns the wheel automatically to reverse you into the spot. 6. Blind-Spot Sensors GM's GPS-based collision detectors can warn you when another car enters your blind spot. 7. Corner Speed An experimental Honda navigation computer anticipates upcoming turns and, if necessary, slows the vehicle to match predetermined safe speeds.

25.  http://en.wikipedia.org/wiki/LIDAR http://en.wikipedia.org/wiki/LIDAR  http://en.wikipedia.org/wiki/Global_Positioning_System http://en.wikipedia.org/wiki/Global_Positioning_System  http://www.gps.gov/ http://www.gps.gov/  http://www.navcen.uscg.gov/gps/default.htm http://www.navcen.uscg.gov/gps/default.htm  http://www.astronautix.com/project/navstar.htm http://www.astronautix.com/project/navstar.htm  http://www.trimble.com/gps/index.shtml http://www.trimble.com/gps/index.shtml  http://inst.wff.nasa.gov/eaarl/ http://inst.wff.nasa.gov/eaarl/  http://www.gpsmaniac.com/gpsmaniac/article/articleDetail.jsp?id=460549 http://www.gpsmaniac.com/gpsmaniac/article/articleDetail.jsp?id=460549  http://en.wikipedia.org/wiki/Darpa_grand_challenge http://en.wikipedia.org/wiki/Darpa_grand_challenge  http://www.popularmechanics.com/science/robotics/2169012.html?page=2 http://www.popularmechanics.com/science/robotics/2169012.html?page=2  http://cs.stanford.edu/group/roadrunner//old/index.html http://cs.stanford.edu/group/roadrunner//old/index.html