The AI Driving Olympics at NeurIPS 2018
Abstract
Despite recent breakthroughs, the ability of deep learning and reinforcement learning to outperform traditional approaches to control physically embodied robotic agents remains largely unproven. To help bridge this gap, we created the 'AI Driving Olympics' (AI-DO), a competition with the objective of evaluating the state of the art in machine learning and artificial intelligence for mobile robotics. Based on the simple and well specified autonomous driving and navigation environment called 'Duckietown', AI-DO includes a series of tasks of increasing complexity -- from simple lane-following to fleet management. For each task, we provide tools for competitors to use in the form of simulators, logs, code templates, baseline implementations and low-cost access to robotic hardware. We evaluate submissions in simulation online, on standardized hardware environments, and finally at the competition event. The first AI-DO, AI-DO 1, occurred at the Neural Information Processing Systems (NeurIPS) conference in December 2018. The results of AI-DO 1 highlight the need for better benchmarks, which are lacking in robotics, as well as improved mechanisms to bridge the gap between simulation and reality.
Cite
@article{arxiv.1903.02503,
title = {The AI Driving Olympics at NeurIPS 2018},
author = {Julian Zilly and Jacopo Tani and Breandan Considine and Bhairav Mehta and Andrea F. Daniele and Manfred Diaz and Gianmarco Bernasconi and Claudio Ruch and Jan Hakenberg and Florian Golemo and A. Kirsten Bowser and Matthew R. Walter and Ruslan Hristov and Sunil Mallya and Emilio Frazzoli and Andrea Censi and Liam Paull},
journal= {arXiv preprint arXiv:1903.02503},
year = {2019}
}
Comments
Competition, robotics, safety-critical AI, self-driving cars, autonomous mobility on demand, Duckietown