AWS Public Sector Blog

Teaching machine learning through robot application development on AWS

A guest post by Intermind Co. Education

Machine learning (ML) isn’t just for the technology industry. Today, machine learning influences research and consumer products and is leading to breakthroughs across industries like healthcare, manufacturing, finance, and retail. In the field of reinforcement learning, machine learning meets the real world when applied to robotics. Knowing this, how can we ensure students are skilled and prepared to leverage the power of this technology?

Intermind Co. is an education group bringing academic programs from leading universities on subjects like machine learning and artificial intelligence to international college students. We recently created a project-based learning experience around the use of Robot Operating System (ROS), the leading open-source framework for writing robot software, and AWS RoboMaker, a service that helps develop, test, and deploy intelligent robotics applications at scale. For our summer 2019 program, we arranged for a group of 160 Chinese university-level students and 20 faculty to visit the United States to learn reinforcement learning through hands-on robot application development.

Developing robot applications can be challenging. Students need prerequisite skills to be successful in these workshops, so we worked with Amazon Web Services (AWS) – including the AWS RoboMaker and AWS Educate programs – to structure the educational content accordingly. Our workshop approach spanned four half-day sessions with students working in teams of four. We introduced students to ROS and AWS RoboMaker, and then transitioned to interactive exercises around the use of the AWS RoboMaker integrated development environment (IDE) and simulation. Students used AWS RoboMaker Cloud extensions, like Amazon CloudWatch data logs and Amazon Kinesis video streams, to interact with their robots. From there, we had students apply their learnings by deploying their robot applications to hardware. We assigned each team a TurtleBot, which facilitated an interactive learning experience.

These workshops provided a framework for teaching reinforcement learning, while exposing students to ROS and AWS RoboMaker.

We had three major takeaways:

  1. Students demonstrated a sense of achievement when seeing their code run on hardware (TurtleBot). This confirmed our belief in hands-on learning.
  2. Students with a programming background in Python or C++ could more quickly learn ROS; therefore, this content is best for intermediate or advanced students with experience in computer programming.
  3. Students with prior AWS experience could more quickly master AWS RoboMaker. Once students felt familiar with AWS services and could navigate the AWS Console, they were more prepared to use AWS RoboMaker.

Our students are empowered to continue exploring AWS RoboMaker back on campus through AWS Educate. We will continue to work with AWS to explore hands-on learning opportunities for our students, including more workshops and hackathons.

Learn more about running your own AWS RoboMaker Workshop.

Questions? Please contact