The AI Driving Olympics at NIPS 2018
Deep learning and reinforcement learning have had dramatic recent breakthroughs. However, the ability to apply these approaches to control real physically embodied agents remains primitive compared to traditional robotics approaches. To help bridge this gap, we are announcing the AI Driving Olympics (AI-DO), which will be a live competition at the Neural Information Processing Systems (NIPS) in Dec. 2018. The overall objective of the competition is to evaluate the state of the art of machine learning and artificial intelligence on a physically embodied platform. We are using the Duckietown [14] platform since it is a simple and well-specified environment that can be used for autonomous navigation. The competition comprises five tasks of increasing complexity - from simple lane following to managing an autonomous fleet. For each task we will provide tools for competitors to use in the form of simulators, logs, low-cost access to robotic hardware and