Interaction and Decision-Making in Autonomous-Driving

A Virtual Workshop at RSS 2020
July 13th

Workshop Description

As an ever-growing number of autonomous vehicles are deployed on public roads, developing robust decision-making algorithms becomes increasingly important. To enable better decision making, recent research efforts have focused on detecting, modelling, and predicting the behavior of traffic participants. The first aim of this workshop is to discuss recent advances, open research challenges, and future directions for robust decision making for autonomous driving. This includes the requirements and advances for situation-awareness pipelines to enable robust decision making, the scientific challenges involved in integration of these pipelines, and the decision-making aspects involved towards enabling robust interactive autonomy. The second aim of this workshop, is to discuss the interplay between prediction and planning, given the multi-agent nature of driving. "Socially-aware" motion planning w.r.t. forecasting models of other agents is often often necessary, but also vice-versa: forecasting w.r.t. plans, to anticipate how a robot’s plan will likely affect surrounding drivers. Given the increasing amount of interest in this area in robotics, computer vision, and machine learning communities, we hope this workshop can be a suitable venue to promote further discussion and developments in this area.



Monday, July 13th, on Pacific Time (UTC-7)


09:30 AM Welcome

09:35 AM Dorsa Sadigh When our Human Modeling Assumptions Fail: Planning, learning, and prediction in near-accident driving scenarios [recording]

10:15 AM Maxim Dolgov Hybrid AI for AD @ Bosch Research [recording]

10:55 AM Contributed talks [recording]

  • Cillian Brewitt
    Autonomous Driving with Interpretable Goal Recognition and Monte Carlo Tree Search
    paper | video
  • Danial Kamran
    On the Challenges of Safe and Scalable Reinforcement Learning for Automated Driving at Intersections
    paper | video
  • Jack Geary
    Altruistic Decision-Making for Autonomous Driving with Sparse Rewards
    paper | video
  • Jierui Lin
    Learning a Perception-Logic Network for Unsupervised Scene Conditioned Driving Behavior
    paper | video

11:15 AM break

11:30 AM Anca Dragan Game-theoretic driving [recording]

12:10 PM Charlie Tang Multi-agent Negotiations via Self-play and Robust Deep Reinforcement Learning [recording]

12:50 PM Contributed talks [recording]


1:10 PM break

2:00 PM Alyssa Pierson Modeling Socially-Aware and Risk-Aware Autonomy [recording]

2:40 PM Adrien Gaidon The 3 R's and P's of Autonomous Driving: Robustness, Randomness, and Risk in Perception, Prediction, and Planning [recording]

3:20 PM Contributed talks [recording]

Combined Learning and Optimisation for Motion Trajectory Prediction with Environment Constraintspaper | video

4:00 PM Changliu Liu Safe Autonomous Driving: Prediction, Planning, and Coordination [recording]

4:40 PM Shengbo Li Distributional Soft Actor-Critic [recording]

5:20 PM Panel [recording]

6:00 PM Goodbye

RSS registration:
RSS portal: (under "Sessions" --> "WS2-1: Interaction and Decision-Making in Autonomous Driving")


Bosch Corporate Research

Toyota Research Institute

Tsinghua University

Break Room

Navigate using the WASD keys

Listen to a particular video by: (1) navigating very close to the video, (2) increasing volume by left-clicking "+", then (3) right-click-and-hold the video

Or to open in a new window go to: