Self-driving DIY Robocars @ Locate

By: Eric Gundersen

Day 1 Donkeycar racing team signups are open. Each team should be made up of no more than 5 people, but honestly we have no way of enforcing this.

Micro self-driving cars rules:

1. No tele-operators.
2. No V2V lasers to intentionally interfere with other cars.
3. Mapping software used to mine bitcoin needs to be disclosed to the SEC.

We‘ll launch the Donkeycar Maps SDK on April 2nd, giving each team 6 weeks to add HD Vector Maps, encoded with the track geometry and libraries, to decode the coordinates for the race trace. Some participants do all analysis on-device, others will transmit the data from their on-board sensors (cameras, sonar, LIDAR, radar, GPS or whatever else you have) via WiFi to a laptop that runs pro-grade AI and robotics software, including TensorFlow, ROS or the Udacity Self-Driving Car Nanodegree toolchain. Both approaches are allowed.

Judging is based on four best-of-class categories:

• Neural networks FPS rate on front facing cameras
• Localization using high percision GPS
• LIDAR implementation under $100k
• Last car standing

We will also give awards to anyone who open sources their training model or code as part of their entry.

See you at Locate.

Eric Gundersen

Self-driving DIY Robocars @ Locate was originally published in Points of interest on Medium, where people are continuing the conversation by highlighting and responding to this story.