You are viewing content from a past/completed QCon

Keynote: Inside a Self-Driving Uber

Location: Cyril Magnin Ballroom

Duration: 9:00am - 10:10am

Day of week: Tuesday

Abstract

Over the course of three years, Uber’s self-driving vehicles have driven over 2 million miles and have completed over 50,000 passenger trips in Pittsburgh and Phoenix. Many of you might be curious as to how we built a fleet of self-driving vehicles capable of driving autonomously in varying terrains and conditions. In this talk, Matt will break down the software components that come together to make a self-driving Uber drive itself. You’ll also learn about how we thoroughly test new software before it is deployed to the fleet.

Speaker: Matt Ranney

Sr. Staff Engineer @UberATG

Matt works on Uber ATG's simulation systems to exercise autonomy software before it gets onto the road. Before that, he worked on distributed systems, architecture, and performance at Uber.

Find Matt Ranney at

Tracks

  • Groking Timeseries & Sequential Data

    Techniques, practices, and approaches, including image recognition, NLP, predictions, & modeling.

  • Deep Learning in Practice

    Deep learning lessons using Tensorflow, Keras, PyTorch, Caffe including use cases on machine translation, computer vision, & image recogition.

  • AI Meets the Physical World

    Where AI touches the physical world, think drones, ROS, NVidia, TPU and more.

  • Papers to Production: CS in the Real World

    Groundbreaking papers make real world impact.

  • Solving Software Engineering Problems with Machine Learning

    Anomaly detection, ML in IDE's, bayesian optimization for config. Machine Learning techniques for more effective software engineering.

  • Predictive Architectures in the Real World

    Case Study focused look at end to end predictive pipelines from places like Salesforce, Uber, Linkedin, & Netflix.