Sponsor: Arunava Majumdar, IBM
Mentor(s):
Arunava Majumdar arunava@us.ibm.com
Jeremy Edmondson jedmond2@ncsu.edu
Background of Company:
IBM has been leading Hardware and Software technologies for over 100 years.
Project Background and Need:
Most racing car scenarios are built with manual racing controls. This project is aimed at autonomous racing using advanced Machine Learning and Deep Learning algorithms.
Problem Description/requirements (List of high-level functionality you expect to see in the end product):
Racing cars have always tested the limits of our understanding of path optimizations along with acceleration and declaration of the vehicle on a winding track. Once multiple racing cars are introduced the driver of the vehicle has to not only optimize the path but avoid any obstacles (cars) in the path. This makes it a very complex problem to solve for an autonomous vehicle.
This project aims to take up this challenge in a phased approach.
--------
Phase I:
--------
Construct a scaled-down version of the car. Use the Open Source NVDIA project to build an autonomous racing car using Tamya TT02 model and Jetson Nano.
https://github.com/NVIDIA-AI-IOT/jetracer
Train and follow the road. Train the car on an oval track.
---------
Phase II:
---------
Connect to the Proximity Network using MQTT protocol to the MQ Queue Manager. Build an application to connect to the Watson IoT Platform to transfer data to be analyzed. Multiple cars should be able to connect to this server and publish information.
On the IBM Cloud the data can then be stored on the Cloud Object Storage bucket. Use Watson Studio to build and train models using the data obtained after every run. Build alternate models using Studio and use Auto AI to check which models work better.
Required Skills / Desired Competencies (in order of importance):
Programming experience (Python, Java)
Embedded hardware and programming
Robotics and mechatronics (sensor and actuator interface)
Computer vision and imaging
Machine learning
Hands-on assembly of mechanical components
How often and how would you be available to meet/chat with the team (Zoom, Hangout, Skype, Phone)?
1hr/week on WebEx, Slack anytime
Will the students be required to sign any of the following before they start with the project? NDA / CDA / IP assignment / IP protection form
No.
System Architecture Diagram - docs.google.com/document/d/1e2Ve1croWZRfrPK_-_f9QkREouZXbYS5obv3qgdQ-zs/edit?usp=sharing