The role servovision in a student autonomous racing vehicle: from theory to experiments

• Grant number: 21/09861-5
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2021
• End date: October 31, 2022
• Field of knowledge: Engineering - Mechanical Engineering
• Principal Investigator: Maira Martins da Silva
• Grantee: Murilo Fantucci Todão
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Autonomous vehicles promote universal access, safety, and energy efficiency. When no driver interference is required, the vehicle needs to be able to control itself in extreme environmental conditions and emergency situations. Some student competitions offer the opportunity for students to design vehicles with this level of autonomy. Among the main tasks of these students are vehicle instrumentation, the definition of data processing algorithms, and the motion planning strategy. In one of these competitions, the vehicle must complete ten laps, as fast as possible, around an unknown track delimited by yellow and blue cones. The proposal in this undergraduate research project is to verify the use of stereo vision for object identification and track mapping. The identification of objects will be performed using Perspective-n-Point and the mapping using the FastSlam 2.0 algorithms. It is expected that evaluations on the qualities and deficiencies of instrumentation and numerical techniques are carried out with this scientific initiation. (AU)