|Version 4 (modified by 8 months ago) ( diff ),|
ROS Based Self Driving Platform Development
The goal of this project is to work on development of the the winlab self driving car simulator. The project includes development of ~1/14 scale vehicles for use as a remote self-driving car testing platform, as well as a virtual simulation environment which will model both the physical vehicles and the testbed environment. Robot Operating System (ROS) will be used for both halves of the project, with the simulation running in Gazebo.
There are several objectives for this project:
- Design and implementation of additional sensors for existing vehicles to allow for remote experimentation
- Incorporation of ROS control into existing car software
- Use of AI/machine learning algorithms for self driving behavior
Due to current operating status at Rutgers, we will most likely not be able to work with the physical hardware until at least July, when Winlab staff will be present to monitor remote use of the vehicles.
- Gazebo Robotic Simulator - Gazebo is a simulator designed for use with ROS-based systems. This is the software that will be used to model the vehicles and their behavior.
- End to End Learning for Self Driving Cars - this paper describes a simple method for training a self driving car with a convolutional neural network.
Week 1 Activities
- Get ORBIT/COSMOS account and familiarize oneself with the testbed procedures
- Review ROS tutorials and try running them on orbit