The Swish AWS DeepRacer is a virtually trained, autonomous vehicle guided by Reinforcement Learning (RL) models. RL is an advanced Machine Learning (ML) technique that can discern complex behaviors without labeled training data and make short term decisions while optimizing for longer-term goals.
Swish competed in the AWS DeepRacer races at the AWS Summit in Washington, DC this year.
We initially thought the Swish team wouldn’t be able to race because our models were trained on the EVO dual-camera system which did not work with the vehicles at the summit that were equipped with only a single camera. Undeterred, we did a quick reset / refocus and came back on the second day with a newly created model developed for the basic single-camera system. With just seven hours of virtual training, the Swish team developed a model that steered the vehicle to the finish line unassisted on its first attempt.
DeepRacer employs the power of AWS SageMaker, a fully managed machine learning service in the Cloud. “With SageMaker, data scientists and developers can quickly and easily build and train machine learning models, and directly deploy them into a production-ready hosted environment. It provides an integrated Jupyter authoring notebook instance for easy access to your data sources for exploration and analysis so you don’t have to manage servers. It also provides common machine learning algorithms that are optimized to run efficiently against extremely large data in a distributed environment.” (https://docs.aws.amazon.com/sagemaker/latest/dg/whatis.html)
If your organization is interested in getting involved with DeepRacer or Reinforcement Learning or would like to learn more about Swish, please feel free to reach out at COETeam@swishdata.com.