Site icon Wil Selby

FormulaPi Autonomous Vehicle Racing

System Modeling ■ Vehicle Control

FormulaPi is an autonomous vehicle racing series and racing club based around the Rasberry Pi. This is an autonomous vehicle race series that started on KickStarter and was designed for people with little hardware or software experience. The league provides everyone with basic software and a common hardware platform. All of the vehicles are maintained at the FormulaPi race course, however, the teams can remotely modify and upload their software before each race.

The series is sponsored by the team at PiBorg. They run and supervise the races, provide the hardware and maintain the initial software repository. The races consist of 23 laps around a 0.5km track with 5 competitors per race. For remote participants, they broadcast the races live online.

Every competitor submits their code before each race, which is then uploaded into identical YetiBorg HS Zero robots. The Yetiborg is powered by a Raspberry Pi Zero, with the code stored on a microSD card. For sensors, the Yetiborg has a Raspberry Pi camera.

The races are hosted at the PiBorg offices. The PiBorg team designed and built the track which is over 22m long and has 5 turns. The track also includes a timing rig to track the vehicles. It also includes colored lanes and starting lights that the software uses to identify the vehicle’s position on the track.

The PiBorg team provides all competitors with a common code base. This software contains the minimum amount of functions needed to process images and control the Yetiborg. The software is only available to competitors and is hosted privately on SourceForge. The intent is to keep the software simple enough for entry level competitors but to allow flexibility for more advanced competitors to modify the software to improve performance.

Subsequent pages detail my progress developing a basic model for the Yetiborg vehicle, developing basic control systems, creating a FormulaPi simulation environment using ROS and Gazebo, and improving the computer vision and control software to prepare for the FormulaPi summer 2017 race series.


Exit mobile version