“How to Program a Self-Driving Car”
Who’s in the Driver’s Seat? The Transformation of Transportation
Tuesday, October 17th, 2017
The Queen MORE INFO
“On Tuesday, October 17, I am excited to be speaking at the TEDx Wilmington Salon about ‘How to Program a Self-Driving Car’.
My talk will highlight the five core components of autonomous vehicles, and illustrate how they work by showing videos of student projects from the Udacity Self-Driving Car Engineer Nanodegree Program.
Those core components are: computer vision, sensor fusion, localization, path planning, and control.
Computer vision is how the car learns about the environment around it through camera images.
Sensor fusion is how the car combines those camera images with radar and laser data to reach a more complete understanding of the world. Sensors like radar and lasers are useful for gathering data like the distance and velocity of nearby objects, which is harder to discern from camera images.
Localization is how we take that information about the surrounding world and then use it to figure out where we are in that world. We all have cellphones with GPS in them, and it might seem tempting to just use GPS to localize ourselves. However, GPS is only accurate to within 1-2 meters. Self-driving cars need single-digit centimeter level accuracy in order to stay in their lanes, which is a much more precise requirement.
Path planning is how we chart a path through the world to get to where we’re going. Path planning software has to make decisions both at the macro level – how to get from the starting point to the destination – and at the micro level – what to do if a cat jumps out in front of the car. The final result of the path planner is the trajectory that the car should follow at any given point in time.
And control is how we actually turn the steering wheel and use the throttle and the brake to execute the trajectory we’ve decided to follow.
That’s how a self-driving car works!
Come out to TEDx Wilmington Salon to learn more.”
David Silver leads the Self-Driving Car Team at Udacity, where he teaches a nine-month program that trains engineers to work in the autonomous vehicle industry. Prior to Udacity, David was a Research Engineer at Ford Motor Company. Before Ford, David worked in engineering and product roles at Candidate Metrics, mSpot, and AOL. He has an MBA from Stanford University, and a BSE in computer science from Princeton University. READ MORE
Who’s in the Driver’s Seat? The Transformation of Transportation :: Tuesday, October 17th, 2017 The Queen MORE INFO