Behavior-driven Autonomous Driving in Unstructured Environments


(BADUE'22)

October 27, 2022 at IROS'22 in Kyoto, Japan !

Overview


Video proceedings on YouTube


Autonomous driving research has advanced significantly through continuous improvements in perception, prediction, and planning. Despite this success, autonomous driving is limited to simple, sparse, and homogeneous traffic scenarios such as wide highways and sparsely populated urban cities. Scenarios like navigating unprotected left turns, unsignalized intersections, and roundabouts require autonomous vehicles to negotiate with human drivers and anticipate their actions, which often depend on the drivers’ behavior that autonomous vehicles cannot predict. Human driver behavior ranges from aggressive to conservative and different behaviors produce different styles; autonomous vehicles struggle to navigate these situations, especially in dense and unstructured traffic. Researchers and practitioners, therefore, have begun research at the intersection of human driver behavior modeling, multi-agent systems, and autonomous driving.

These three areas, combined, complement academic and industry work in perception, prediction, and planning. This workshop provides a platform to highlight recent efforts that advance behavior-driven autonomous driving, simulation, and ADAS with applications in human driver behavior modeling, multi-agent systems, and autonomous driving. Through invited talks, panel discussions, and paper presentations, attendees will become familiar with the latest research and network for new collaborations. Our jective for this workshop is to amplify the impact of behavior-driven autonomous driving research in both academia and industry, resulting in safer, robust, and confident autonomous vehicles.

One of the main goals of our workshop is to bridge the gap between the Multi-agent and Multi-Robot systems, Cognitive Robotics, and the Autonomous Driving community. The organizers and speakers are from top academic institutes (Stanford, Berkeley, CMU, Tsinghua) and industry organizations (Tesla, Waymo, Wayve, TRI) and have a lot of real world experience as well as a strong publishing record in dealing with these aspects. The organizers and speakers have also collected some challenging datasets on autonomous driving which are a great test bed for addressing research problems in cooperation, teaming, driver behavior, and game-theoretic aspects. Finally, we are proud to support great diversity in our team including age, gender, ethnicity, and location.

          

Follow us on Twitter to stay updated !

Invited Speakers

Ashok Elluswamy

Tesla

Nick Rhinehart

University of California, Berkeley

Rowan McAllister

Toyota Research Institute

Mac Schwager

Stanford University

Alyssa Pierson

Boston University

Katie Driggs-Campbell

UIUC

Peter Stone

UT Austin, Sony AI

Hang Zhao

Tsinghua University

Shimon Whiteson

Waymo Research

Jamie Shotton

Wayve

Raquel Urtasun

Waabi

Dinesh Manocha

UMD

Call for Papers

We invite participants to submit either short (4+n) or long papers (8+n). We encourage the submission of early ideas, late-breaking results, position papers, or open research questions that are likely to generate interesting discussions. Work published elsewhere is allowed. Accepted papers will be presented in a poster session and selected papers as spotlight talks. All submitted contributions will go through a single blind review process.


Topics include, and are not limited to:


The specific goals of the workshop will be to discuss ideas around following topics:

  • Perception in unstructured environments
  • Mapping and localization
  • Recognizing novel objects
  • Multi-agent trajectory forecasting
  • Multi-agent behavior prediction
  • Driver behavior modeling
  • Modeling human factors
  • Modeling human interactions in autonomous driving
  • Coordination and competition among multiple autonomous agents
  • Teaming in autonomous driving
  • Cooperative navigation
  • Learning for multi-agent navigation
  • Theory for multi-agent systems
  • Autonomous racing
  • Game-theoretic planning
  • Multi-agent decision making
  • Reinforcement learning in autonomous driving
  • ADAS, simulation, and software-driven approaches


Submission

Submissions closed.

Important Dates

  • Submission deadline: September 20, 2022 September 23, 2022 (Anywhere on Earth).
  • Notification of acceptance: September 27, 2022.
  • Camera Ready Submission: October 4, 2022.
  • Workshop day: October 27, 2022.
**If you wish to attend in-person, please follow the IROS 2022 workshop guidelines here and fill in the participation form here . Filling the form is important because the room assignments at the venue will be based on number of registered participants.**

Best paper award

We will be awarding 1-2 best student paper awards (sponsored by Wayve)!

Endorsements

Our workshop is endorsed by the following RAS technical committees:

Program

Zoom Link



Room 7/Room E/ThWF-7

If you haven’t completed the registration, please visit the registration desk for in-person participation. For online registration, the virtual registration using the JTB is currently closed but will be reopened soon.

Time Event Details
09:00 - 09:35 Introductory Remarks  
09:35 - 10:00 Talk 1 - Dinesh Manocha Behavior Modeling in Dense and Heterogeneous Traffic for Autonomous Driving
10:00 - 10:25 Talk 2 - Jamie Shotton Learning a Globally Scalable Driving Intelligence
10:25 - 10:40 Coffee Break Coffee locations (yellow coffee icon)
10:40 - 11:05 Talk 3 - Alyssa Pierson Modeling Interactions within Multi-Agent Autonomous Driving
11:05 - 11:30 Talk 4 - Ashok Elluswamy Scalable Self-Driving
11:30 - 11:55 Talk 5 - Peter Stone Reward (Mis)design for Autonomous Driving and Accumulating Safety Rules from Catastrophic Action Effects
11:55 - 13:00 Lunch  
13:00 - 13:25 Talk 6 - Rowan McAllister Robust Behavior Models for Autonomous Driving
13:25 - 13:50 Talk 7 - Nick Rhinehart Contingency Planning with Learned Models of Behavioral and Perceptual Uncertainty
13:50 - 14:30 Spotlight Talks See below for details
14:30 - 14:55 Talk 8 - Mac Schwager Game Theory for Simultaneous Behavior Prediction and Trajectory Planning in AVs
14:55 - 15:20 Talk 9 - Hang Zhao Interactive Motion Prediction and Simulation via Explicit Relation Modeling
15:20 - 15:35 Coffee Break Coffee locations (yellow coffee icon)
15:35 - 16:00 Talk 10 - Shimon Whiteson Learning Realistic & Diverse Agents for Autonomous Driving Simulation
16:00 - 16:55 Panel Discussion See below for details
16:55 - 17:00 Concluding Remarks  

Accepted Spotlight Papers (in order of presentation)

  1. Exploring Contrastive Learning with Attention for Self-Driving Generalization
    Laura Y Zheng (University of Maryland, College Park); Yu Shen (University of Maryland - College Park); Ming C Lin (UMD-CP & UNC-CH )
  2. Inverse Reinforcement Learning with Hybrid-weight Trust-region Optimization and Curriculum Learning for Autonomous Maneuvering
    Yu Shen (University of Maryland - College Park); Weizi Li (University of North Carolina at Chapel Hill); Ming C Lin (UMD-CP & UNC-CH )
  3. Imitative Planning using Conditional Normalizing Flow
    Shubhankar Agarwal (University of Texas at Austin); Harshit Sikchi (University of Texas at Austin); Cole Gulino (Uber Advanced Technologies Group); Eric Wilkinson (Uber Advanced Technologies Group ); Shivam Gautam (Aurora Innovations Inc.)
  4. Motion Primitives Based Kinodynamic RRT for Autonomous Vehicle Navigation in Complex Environments
    Shubham Kedia (University of Illinois, Urbana-Champaign); Sambhu Harimanas Karumanchi (University of Illinois, Urbana-Champaign)
  5. Real-time Autonomous Parking in Unstructured Scenarios with an Indirect Optimal Control Approach
    Edoardo Pagot (University of Trento); Mattia Piccinini (University of Trento); Alice Plebe (University of Trento); Enrico Bertolazzi (University of Trento); Francesco Biral ( University of Trento)
  6. Data-Efficient Collaborative Decentralized Thermal-Inertial Odometry
    Vincenzo Polizzi (Robotics and Perception Group, University of Zurich); Robert Hewitt (Jet Propulsion Laboratory, California Institute of Technology); Javier Hidalgo-Carrió (University of Zurich); Jeff Delaune (Jet Propulsion Laboratory, California Institute of Technology); Davide Scaramuzza (University of Zurich & ETH Zurich, Switzerland)
  7. Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion
    Suman Ghosh (TU Berlin); Guillermo Gallego (TU Berlin)

Panel:

"What are some of the research and engineering challenges in terms of pushing AVs to level 3/4/understanding human driver behavior in unstructured environments?"

Jie Tan

Google Brain

Joydeep Biswas

UT Austin

Rowan McAllister

Toyota Research Institute

Hang Zhao

Tsinghua University

Shimon Whiteson

Waymo Research

Awards

The best paper award ($1000, sponsored by Wayve) goes to Imitative Planning using Conditional Normalizing Flow
Shubhankar Agarwal (University of Texas at Austin); Harshit Sikchi (University of Texas at Austin); Cole Gulino (Uber Advanced Technologies Group); Eric Wilkinson (Uber Advanced Technologies Group ); Shivam Gautam (Aurora Innovations Inc.)

Honorable mention to Inverse Reinforcement Learning with Hybrid-weight Trust-region Optimization and Curriculum Learning for Autonomous Maneuvering
Yu Shen (University of Maryland - College Park); Weizi Li (University of North Carolina at Chapel Hill); Ming C Lin (UMD-CP & UNC-CH)

Organizers

Rohan Chandra

University of Maryland/ UT Austin

Anca Dragan

University of California, Berkeley

Negar Mehr

UIUC

Ben Sapp

Waymo

Dinesh Manocha

University of Maryland