logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-04022022-192854


Tipo di tesi
Tesi di laurea magistrale
Autore
GIOVE, ANDREA
URN
etd-04022022-192854
Titolo
Motion planning and forecasting for an autonomous racing car
Dipartimento
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
INGEGNERIA ROBOTICA E DELL'AUTOMAZIONE
Relatori
relatore Prof.ssa Pallottino, Lucia
correlatore Ing. Caporale, Danilo
Parole chiave
  • motion planning
  • motion forecasting
  • vehicle
  • racing
  • forecasting
  • planning
  • autonomous
Data inizio appello
05/05/2022
Consultabilità
Non consultabile
Data di rilascio
05/05/2092
Riassunto
This work illustrates the motion planning and forecasting modules of er.autopilot, the autonomous software stack develop by the TII Euroracing team for the Dallara AV21, a fully autonomous racing car that has taken part in the competitions of the Indy Autonomous Challenge. A motion forecasting algorithm based on the Kalman filter has been used to predict the future trajectories of the opponents’ car. The role of the motion planning module is to generate a trajectory that avoids the surrounding obstacles. To do it, an approach working in a Frenét frame has been used. The software stack has been tested at the Indianapolis Motor Speedway and at the Las Vegas Motor Speedway, where the car participated in an overtaking competition. The motion planning modules, in conjunction with all the other modules of the stack, has been capable of generating safe and smooth overtaking trajectories reaching a speed of 60 m/s (∼ 215 kph).
File