The Competition

Autonomous driving (AD) is the next frontier of artificial intelligence and machine learning. Intending to further research in AD, we invite you to participate in an autonomous driving competition organised by Huawei Technologies Ltd. and academic collaborators.

The competition is now live at codalab:

2022 Neurips Driving SMARTS Competition

Tasks and evaluation

This competition seeks to advance autonomous driving by developing agents that can drive as quickly and safely as possible from the start to destination amid background traffic. Data for the competition consists of large-scale naturalistic driving data replayed within SMARTS simulation environment. The following typical driving scenarios are tested: cruising, overtaking, merging, left turns at unsignalized intersections and being cut off by another vehicle. These scenarios are mined from the naturalistic data, manipulated and replayed in SMARTS. For some scenarios, interactive background vehicles are added in SMARTS.

Agents will be ranked according to metrics on safety and comfort (smoothness and safe driving), task completion (% of completed scenarios), traffic rule violation, and completion time.

Competition tracks

There are two tracks in the competition.

Track 1: The participants may use any method and training data to develop their solutions.

Track 2: The partcipants are only allowed to train their methods on the offline datasets.

Winners in each track will receive cash prizes and will get a chance to present their innovative solutions during the virtual ceremony.

Return to top

Competition timeline

The NeurIPS 2022 Driving SMARTS competition is a programming competition organised by Huawei Noah’s Ark Lab with a number of academic collaborators from Canadian universities.

  • Aug. 1, 2022: competition opens.
  • Nov. 1, 2022: competition closes at 11:59pm Pacific Time.
  • Nov. 5, 2022: finalists will be announced and will be asked to submit their code and models for evaluation.
  • Nov. 15, 2022: winning teams announced.

Return to top

Prizes

Top participants in each track will receive the following prizes:

  • Gold US$6000
  • Silver US$4000
  • Bronze US$2000

Additional prizes:

  • US$1000 for the most innovative approach out of top-6 entries in both tracks
  • US$1000 given to one of the valid submissions not in top-3 positions in either track

Return to top

General Rules

  • Participants can be a single entrant or part of a team;
  • Participants must be registered for the competition prior to submitting an entry;
  • Participants must be solely responsible for creating the submission (receiving supervision or advice from supervisors or colleagues is permitted);
  • Participants must be able to share their training and inference code and trained models with the organizers;
  • For the participants or a team to be eligible for receiving awards, each member must satisfy the following conditions:
    • be at least 18 years old or age of majority in place of residence;
    • not be an organizer of this competition nor employee of Huawei or a family member of a competition organizer;
  • Any submissions entered after the competition closes will be automatically disqualified.

Return to top

How to enter

  • The individual participant or, if a team is entering, a team representative, must register with the Organiser through the “2022 Neurips Driving SMARTS Competition” site.
  • The participants will be provided login details to CodaLab to submit a competition entry;
  • Starter kit and necessary documentation will be available upon registration;
  • The entry sumitted by the participant will consist of the pretrained model and inference code. Select participants who opted to compete in track 2 will be requested to submit their training code.
  • Participants may submit up to 3 entries to the competition.

Return to top

Submission site

The competition is run from the following site: Driving SMARTS Competition submission

How winners are determined

  • Submissions for Track 1 will be automatically evaluated on a test set and the results will be posted on the public leaderboard hosted on CodaLab.
  • Top-6 finalists in Track 1 that use offline methods will be invited to submit their training and inference code. The organizers will train and evaluate the models on the withheld dataset.
  • Winners of Track 2 will be determined based on the performance of the models trained by the Organizer.
  • The organizers will work with the participants who selected Track 2 to run their training code, participants may be asked to provide additional documentation to facilitate this process.

Return to top

FAQ

Official rule clarifications will be posted here.

Return to top

Competition Organizing Committee

  • Amir Rasouli
    • Senior Staff Engineer, Huawei Noah’s Ark Lab
  • Randy Goebel
    • Professor, University of Alberta
  • Adam Scibior
    • CTO and co-founder, Inverted AI
  • Matthew E. Taylor
    • Associate Professor, University of Alberta
  • Iuliia Kotseruba
    • PhD Candidate, York University
  • Tianpei Yang
    • Postdoctoral Researcher, University of Alberta
  • Soheil Alizadeh
    • Research Engineer, Huawei Noah’s Ark Lab
  • Montgomery Alban
    • Senior Software Engineer, Huawei Noah’s Ark Lab
  • Florian Shkurti
    • Asisstant Professor, University of Toronto
  • Yuzheng Zhuang
    • Senior Research Scientist, Huawei Noah’s Ark Lab
  • Kasra Rezaee
    • Staff Engineer, Huawei Noah’s Ark Lab
  • Xinyu Wang
    • ADS Planning and Control Chief Architect, IAS BU
  • Weinan Zhang
    • Associate Processor, Shanghai Jiao Tong University
  • Xi Chen
    • Senior Principal Engineer, Huawei Noah’s Ark Lab & Adjunct Professor, McGill University

      Advisers

  • Animesh Garg
    • Assistant Professor, University of Toronto
  • David Meger
    • Assistant Professor, McGill University
  • Jun Luo
    • Distinguished Researcher, Huawei Noah’s Ark Lab
  • Liam Paull
    • Assistant Professor, University of Montreal

Return to top

Contact Us

Organizers can be reached at smarts4ad@gmail.com.

Return to top

About Noah’s Ark Lab

About Huawei

The Noah’s Ark Lab is the AI research center for Huawei Technologies, located in Hong Kong, Shenzhen, Beijing, Shanghai, Xi’an, London, Paris, Toronto, Montreal, Edmonton, etc.

The mission of the lab is to make significant contributions to both the company and society by innovating in artificial intelligence, data mining and related fields. Mainly driven by long term and big impact projects, research in the lab also tries to advance the state of the art in the fields as well as to harness the products and services of the company, at each stage of the innovation process.

As a world class research lab, we are pushing the frontier of research and development in all areas that we work in.We dare to address both the challenges and opportunities in this era of AI and big data, to revolutionize the ways in which people work and live, and the ways in which companies do business, through intelligentization of all processes, with the slogan ‘from big data to deep knowledge’.

Research areas of the lab include computer vision, natural language processing, search & recommendation, decision and reasoning ,AI theory. Founded in 2012, the lab has now grown to be a research organization with many significant achievements in both academia and industry. We welcome talented researchers and engineers to join us to realize their dreams.

View more details

Return to top