Motional's Open Source Robotics Challenges: nuPlan and nuReality
Paul Schmitt will cover a couple of exciting updates from Motional Autonomous Vehicle research.
Introducing nuPlan! Motional is now releasing the 1300h nuPlan dataset consisting of human driving data with high-level scenario annotation. Furthermore, I give an overview of the nuPlan motion planning challenge. In this competition, competitors will measure the performance of their decision-making algorithm that will be controlling an AV. The performance of the submissions will be measured in three challenges including a closed-loop simulation with reactive agents.
Imagine this. You’re walking down a street in a busy city and, as you’re about to cross the road, you see a vehicle approaching. Something gives you pause. You look closer, and you realize the driver’s seat is empty. There’s no one behind the wheel, and the car appears to be driving itself. What would you do? How would you feel? What could the vehicle do or show to help you feel better? At Motional our goal is to make driverless vehicles a safe, reliable, and accessible reality. A key part of our mission is to design our vehicles to integrate into society ... for the benefit of society. nuReality is an open source VR environment for researchers to help tackle these important challenges.