1 of 8

Self-Driving Vehicle Project: Week 9

Group Members: Sandeep Alankar, Adas Bankauskas, Malav Majmudar, Abia Mallick, Zhuohuan Li, Anthony Siu, Aayush Agnihotri, Lohith Bodipati

2 of 8

Zhuohuan Li (GR)

Sandeep Alankar (UG)

Anthony Siu (UG)

Who we are

3 of 8

Malav Majmudar (UG)

Adas Bankauskas (UG)

Abia Mallick (UG)

Who we are

4 of 8

Lohith Bodipati (HS)

Who we are

Aayush Agnihotri (HS)

5 of 8

Project Objectives

  • Build a fully functional self-driving vehicle
  • Incorporation of ROS control into existing car software
  • Use of AI/machine learning algorithms for self-driving behavior
  • Use Gazebo to map out simulations
  • Building the physical model at WINLAB and testing its autonomy in a real environment

6 of 8

Current Progress

  • Switched to ROSARIA, now using ROS nodes to connect to and wirelessly drive the robot
  • Configured ROS nodes such that training data consisting of both imaging and robot commands can be recorded simultaneously
  • Began collecting data through the rosbag node
  • Properly explored the gazebo simulation, expanding on models and the world

​

​

7 of 8

Future Plans

  • Implement self-driving algorithms on smaller mobile robots
    • Use RealSense camera feed and corresponding steering inputs when navigating around WINLAB as training data
  • Train the robot using one of the GPU nodes in the office, specifically “grid”
  • Explore ROS scripts for steering and properly configure ROSARIA onto smaller robots
  • Finish up the final presentation, poster, and website:

​

8 of 8

Any Questions?