Fresh Perspectives on the Future of Autonomous Driving
ICRA 2022 workshop, May 27th

About the Workshop

This workshop aims to foster communication around current paradigms for autonomous vehicles. While we see sufficient maturity in all parts of the classical self-driving stack, their combined performance leaves room for improvement. In the past years, ML-first solutions have been showing promising results, not only in simulation or simplified scenarios, but also in real-world, complex environments. We want to open up the discussion on the challenges that need to be solved in order to enable the next generation of AVs and to encourage new ideas regarding their scalability and safety.

Call for Papers

We invite submissions to the Fresh Perspectives on the Future of Autonomous Driving workshop, hosted at ICRA 2022.

Paper Topics

A non-exhaustive list of relevant topics:

  • Approaches to autonomous driving that break from traditional interfaces or abstractions

    • End-to-end approaches to autonomous driving

    • Approaches that account for interactions between traditional subcomponents (e.g., between perception and planning)

  • Learned methods for planning and control and their ability to generalize

    • Learning from demonstrations / imitation learning

    • Reinforcement learning

    • Reward function learning

  • The collection, curation, and sampling of datasets for end-to-end or learned decision making approaches

  • Methods for validating / evaluating the performance of end-to-end / learned approaches

    • Benchmarks

    • Simulation

  • Methods for interpreting or debugging learned approaches

Submission Guidelines

  • Submission Portal: CMT

  • Format:

  • Dual Submission: We accept dual submissions, but the manuscript must contain substantial original contents not submitted to prior conferences, workshop, or journal.

  • Non-archival: The workshop is a non-archival venue and will not have official proceedings. Workshop submissions can be subsequently or concurrently submitted to other venues.

  • Visibility: Submissions and reviews will be private. Only accepted papers will be made public.

Review and Selection

  • The review process will be double-blind. As an author, you are responsible for anonymizing your submission. You should not include author names, author affiliations, or acknowledgements in your submission.

  • All accepted papers will be presented as posters. The guidelines for the posters are the same as at the main conference.

  • At least one co-author of each accepted paper is expected to register for ICRA 2022 and attend the poster session. Remote attendance permitted.

    • If you need a Visa to enter the US, please apply for one as early as possible. See Visa information provided on the ICRA website.

  • All the accepted submissions will be available on our workshop website, though authors could indicate explicitly if they want to opt out.

Important Dates

  • Extended paper submission deadline : April 25th, 2022 (anywhere on earth)

  • Notification to authors: May 9th, 2022

Information for authors of accepted papers

  • Posters: Authors should prepare a poster to be presented at the conference.

    • The ICRA 2022 poster guidelines suggest a poster no larger than 60" wide and 40" tall (1.5m wide x 1m tall).

    • The following are some poster printing options near the Pennsylvania Convention Center:

      • FedEx Office Print & Ship Center, located at 1201 Market St, Philadelphia, PA 19107, phone number: +1 (215) 923-2520

      • Media Copy, located at 1315 Walnut St # 1, Philadelphia, PA 19107, phone number: +1 (215) 717-5151

Speakers

Adrien Gaidon

Toyota Research Institute

Schedule

All events will be held in the Pennsylvania Convention Center, Room 118 B. Located at 1101 Arch St, Philadelphia, PA 19107

Accepted Papers

Improving Efficiency of Attention-based Models for Motion Prediction

Marcos Conde, Miguel Eduardo Ortiz Huamani, Carlos Gómez-Huélamo


Sociotechnical Specification for the Broader Impacts of Autonomous Vehicles

Thomas Gilbert, Aaron Snoswell, Michael Dennis, Rowan McAllister, Cathy Wu


Uncertainty estimation for Cross-dataset performance in Trajectory prediction

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou, Bogdan Stanciulescu, Fabien Moutarde


Coordinated Multi-Agent Motion Planning via Imitation Learning

Andrei Ivanovic, Rowan McAllister, Ashkan Mirzaei, Igor Gilitschenski


Towards Transferable Interactive Policies for Automated Driving with Hidden Parameter Block MDPs

Danial Kamran, Etienne Bührle


Parametric Control Barrier Functions based Adaptive Safe Control for Heterogeneous Autonomous Vehicles

Yiwei Lyu, Wenhao Luo, John Dolan


Is Anyone There? Learning a Planner Contingent on Perceptual Uncertainty

Charles Packer, Nicholas Rhinehart, Rowan McAllister, Matthew Wright, Xin Wang, Jeff He, Sergey Levine, Joseph Gonzalez


Learning and Predicting Multimodal Vehicle Action Distributions in a Unified Probabilistic Model Without Labels

Charles Richter, Patrick Barragan, Sertac Karaman


Estimation of Appearance and Occupancy Information in Bird’s Eye View from Surround Monocular Images

Sarthak Sharma, Unnikrishnan Nair, Udit Singh Parihar, Midhun Menon, Srikanth Vidapanakal


LiDAR-as-Camera for End-to-End Driving

Ardi Tampuu, Tambet Matiisen, Romet Aidla


Group Distributionally Robust Reinforcement Learning

Mengdi Xu, Peide Huang, Visak Kumar, Jielin Qiu, Chao Fang, Kuan-Hui Lee, Xuewei Qi, Henry Lam, Bo Li, Ding Zhao

Organizers

Anthony Hu

Cambridge

Rowan McAllister

Toyota Research Institute

Peter Ondruska

Woven Planet

Błażej Osiński

University
of Warsaw

Blake Wulfe

Toyota Research Institute

Sergey Zagoruyko

Woven Planet

Program Committee

Contact

icra2022av@googlegroups.com