Autonomous Course Navigation by High-Speed 1/10 Scale Racecars Using Lidar and Passive Stereo Camera

School Name

Governor's School for Science & Mathematics

Grade Level

12th Grade

Presentation Topic

Engineering

Presentation Type

Mentored

Mentor

Mentor: Sertac Karaman, Massachussets Institute of Technology

Abstract

The field of autonomous vehicles is rapidly expanding. Companies like Google and Tesla have been on the forefront of these advances. This project aimed to explore the challenges of autonomous vehicles through scale model cars. Our Rapid Autonomous Complex-Environment Competing Ackermann-Steering Robots (RACECARs) were outfitted with a 270° laser radar (LiDAR) and a color stereo camera and ran Ubuntu for ARM processors using the open-source Robot Operating System (ROS) software library. The project was broken into weeks with building goals culminating in the completion of a racecourse. The first goal was to use LiDAR for autonomous wall-following. The second goal was to identify colored flags and turn based on the color, following the correct wall. The next focus was on space exploration and identifying a greater variety of colored flags. Our work shed light on the pitfalls of autonomous navigation and the path that future work will follow.

Location

Wall 223

Start Date

3-25-2017 9:15 AM

Presentation Format

Oral and Written

Group Project

No

COinS
 
Mar 25th, 9:15 AM

Autonomous Course Navigation by High-Speed 1/10 Scale Racecars Using Lidar and Passive Stereo Camera

Wall 223

The field of autonomous vehicles is rapidly expanding. Companies like Google and Tesla have been on the forefront of these advances. This project aimed to explore the challenges of autonomous vehicles through scale model cars. Our Rapid Autonomous Complex-Environment Competing Ackermann-Steering Robots (RACECARs) were outfitted with a 270° laser radar (LiDAR) and a color stereo camera and ran Ubuntu for ARM processors using the open-source Robot Operating System (ROS) software library. The project was broken into weeks with building goals culminating in the completion of a racecourse. The first goal was to use LiDAR for autonomous wall-following. The second goal was to identify colored flags and turn based on the color, following the correct wall. The next focus was on space exploration and identifying a greater variety of colored flags. Our work shed light on the pitfalls of autonomous navigation and the path that future work will follow.