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 present 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,” the 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. In this paper we will describe the AI-DO 1 including the motivation and design objections, the challenges, the provided infrastructure, an overview of the approaches of the top submissions, and a frank assessment of what worked well as well as what needs improvement. 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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
AMOD competition website https://www.amodeus.science/.
- 2.
The performance rules of AI-DO http://docs.duckietown.org/DT18/AIDO/out/aido_rules.html.
- 3.
For more information, this technique is described in further depth at the following URL: https://www.balena.io/blog/building-arm-containers-on-any-x86-machine-even-dockerhub/.
- 4.
Duckietown logs database: http://logs.duckietown.org/.
- 5.
Accessible online at https://github.com/iasawseen/MultiServerRL.
- 6.
Any submission is visualized on https://challenges.duckietown.org/v3/ by clicking its submission number.
References
Jacky Baltes, Kuo-Yang Tu, Soroush Sadeghnejad, and John Anderson. HuroCup: competition for multi-event humanoid robot athletes. The Knowledge Engineering Review, 32, e1, 2017.
Sven Behnke. Robot competitions-ideal benchmarks for robotics research. In Proc. of IROS-2006 Workshop on Benchmarks in Robotics Research. Institute of Electrical and Electronics Engineers (IEEE), 2006.
Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. Openai gym, 2016.
Martin Buehler, Karl Iagnemma, and Sanjiv Singh. The 2005 DARPA grand challenge: the great robot race, volume 36. Springer, 2007.
Roger Buehler, Dale Griffin, and Michael Ross. Inside the planning fallacy: The causes and consequences of optimistic time predictions. In Gilovich, Griffin, and Kahneman, 02 2019. doi:10.1017/CBO9780511808098.016.
Devendra Singh Chaplot, Emilio Parisotto, and Ruslan Salakhutdinov. Active Neural Localization. In International Conference on Learning Representations, 2018. http://dx.doi.org/https://openreview.net/forum?id=ry6-G_66b.
Maxime Chevalier-Boisvert, Florian Golemo, Yanjun Cao, Bhairav Mehta, and Liam Paull. Duckietown environments for openai gym. https://github.com/duckietown/gym-duckietown, 2018.
Dario Floreano, Francesco Mondada, Andres Perez-Uribe, and Daniel Roggen. Evolution of embodied intelligence. In Embodied artificial intelligence, pages 293–311. Springer, 2004.
Scott Fujimoto, Herke van Hoof, and Dave Meger. Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477, 2018.
Andreas Geiger, Philip Lenz, and Raquel Urtasun. Are we ready for autonomous driving? the kitti vision benchmark suite. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 3354–3361. IEEE, 2012.
Peter Henderson, Riashat Islam, Philip Bachman, Joelle Pineau, Doina Precup, and David Meger. Deep reinforcement learning that matters. In Thirty-Second AAAI Conference on Artificial Intelligence, 2018.
Irina Higgins, Arka Pal, Andrei Rusu, Loic Matthey, Christopher Burgess, Alexander Pritzel, Matthew Botvinick, Charles Blundell, and Alexander Lerchner. {DARLA}: Improving Zero-Shot Transfer in Reinforcement Learning. In Proceedings of the 34th International Conference on Machine Learning (ICML), volume 70, pages 1480–1490, 2017.
Nick Jakobi, Phil Husbands, and Inman Harvey. Noise and the reality gap: The use of simulation in evolutionary robotics. In European Conference on Artificial Life, pages 704–720. Springer, 1995.
Ł. Kidziński, S. P. Mohanty, C. Ong, J. L. Hicks, S. F. Carroll, S. Levine, M. Salathé, and S. L. Delp. Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning. ArXiv e-prints, 3 2018.
Hiroaki Kitano, Minoru Asada, Yasuo Kuniyoshi, Itsuki Noda, and Eiichi Osawa. Robocup: The robot world cup initiative. In Proceedings of the first international conference on Autonomous agents, pages 340–347. ACM, 1997.
Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971, 2015.
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. Human-level control through deep reinforcement learning. Nature, 518 (7540): 529, 2015.
Edwin Olson. Apriltag: A robust and flexible visual fiducial system. In IEEE International Conference on Robotics and Automation (ICRA), pages 3400–3407, 2011.
Nobuyuki Otsu. A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9 (1): 62–66, 1979.
Liam Paull, Jacopo Tani, Heejin Ahn, Javier Alonso-Mora, Luca Carlone, Michal Cap, Yu Fan Chen, Changhyun Choi, Jeff Dusek, Yajun Fang, and others. Duckietown: an open, inexpensive and flexible platform for autonomy education and research. In Robotics and Automation (ICRA), 2017 IEEE International Conference on, pages 1497–1504. IEEE, 2017.
Rolf Pfeifer and Christian Scheier. Understanding intelligence. MIT press, 2001.
Daniel Pickem, Paul Glotfelter, Li Wang, Mark Mote, Aaron Ames, Eric Feron, and Magnus Egerstedt. The robotarium: A remotely accessible swarm robotics research testbed. In 2017 IEEE International Conference on Robotics and Automation (ICRA), pages 1699–1706. IEEE, 2017.
The Duckietown Project. The duckiebook. http://docs.duckietown.org/, Feb. 2019a. Accessed: 2019-02-24.
The Duckietown Project. Duckietown project website. http://duckietown.org/, 2019b. Accessed: 2019-02-24.
Claudio Ruch, Sebastian Hörl, and Emilio Frazzoli. Amodeus, a simulation-based testbed for autonomous mobility-on-demand systems. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pages 3639–3644. IEEE, 2018.
Richard S Sutton and Andrew G Barto. Reinforcement learning: An introduction. MIT press, 2018.
Josh Tobin, Rachel Fong, Alex Ray, Jonas Schneider, Wojciech Zaremba, and Pieter Abbeel. Domain randomization for transferring deep neural networks from simulation to the real World. ArXiv, 2017. ISSN 21530866. http://dx.doi.org/10.1109/IROS.2017.8202133.
Acknowledgements
We would like to thank NeurIPS and in particular Sergio Escalera and Ralf Herbrich for giving us the opportunity to share the AI Driving Olympics with the machine learning community. We are grateful to Amazon AWS and Aptiv for their sponsorship and hands-on help that went into this competition. We are also grateful to the many students in Montréal, Zurich, Taiwan, Boston, Chicago, and many others that have shaped Duckietown and AI-DO into what they are today.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zilly, J. et al. (2020). The AI Driving Olympics at NeurIPS 2018. In: Escalera, S., Herbrich, R. (eds) The NeurIPS '18 Competition. The Springer Series on Challenges in Machine Learning. Springer, Cham. https://doi.org/10.1007/978-3-030-29135-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-29135-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29134-1
Online ISBN: 978-3-030-29135-8
eBook Packages: Computer ScienceComputer Science (R0)