Join the AWS JPL Open-Source Rover Challenge
Want to leave your mark on the unfolding history of space exploration while at the same time hone your hacking skills? We have the right challenge for youthe AWS JPL Open-Source Rover Challenge – a virtual hackathon which runs through February 21, 2020.
Through the AWS JPL Open-Source Rover Challenge, space enthusiasts, robotics developers, and hobbyists can use their skills to improve how rovers on Mars operate to help unlock the secrets of the universe. As part of the challenge, contestants will use machine learning to autonomously operate the virtual Open-Source Rover created by NASA’s Jet Propulsion Laboratory (JPL) to explore the surface of Mars. Contestants will use AWS RoboMaker for the simulation and Amazon SageMaker to build and train their machine learning models.
Here is what you need to do. Build and train a reinforcement learning (RL) model on AWS to autonomously drive JPL’s Open-Source Rover between given locations in a simulated Mars environment with the least amount of energy consumption and risk of damage. We have published all the resources you need to get started in this GitHub repo, including a reference architecture, detailed instructions to set up your simulation and machine learning environments, a virtual model of JPL’s Open-Source Rover, the simulated Mars world, and a scoring function that aggregates the time taken, fuel consumed, and vehicle wear and tear.
You will submit your trained RL model along with your code. We will evaluate all submitted models based on the weighted score and choose the top scoring submissions as winners. The highest scoring solution will also be incorporated into the JPL Open-Source Rover project for future builders to use.
Registered participants will compete for a $15,000 grand prize and a $5,000 runner-up prize. In addition, the first 100 eligible submissions will each receive $250 in AWS credits.