This workshop will be held at the 35rd IEEE Intelligent Vehicles Symposium (IV), on June 2 - 5, 2024 Jeju Shinhwa World, Jeju Island, Korea
Topics
The topics of interest of the workshop include, but are not limited to:
- Cooperative and comprehensible motion planning
- Probabilistic decision making and motion planning (including MDPs, POMDPs, MMDPs)
- Probabilistic behavior prediction (with help of semantic high-definition maps)
- Second-order effects in heavy interactive scenarios
- Evaluation and benchmarking of the aforementioned topics
Important Deadlines:
February 01, 2024: Workshop Paper Submission Deadline (firm deadline, no extension)March 30, 2024: Workshop Paper Notification of AcceptanceApril 22, 2024: Workshop Final Paper Submission Deadline- Workshop: Eorimok Room. 8:30 - 16:30. 2nd of June
Please check the official program for potential updates: https://ieee-iv.org/2024/program/
Workshop Content
Research on Automated Vehicles has experienced vast progress over the last decades. Today, first prototypes are sufficiently safe to drive on selected roads in public traffic. Nevertheless, safety comes at the price of overly conservative behavior, leading to inconvenient situations, for example, at unprotected left turns or merging scenarios. Presumably, the main reasons for this behavior include (a) errors in the prediction of other traffic participants, especially in interactive scenarios and (b) the lack of probabilistic considerations in motion planning.
Comfortable Automated Driving: While safety should never be put at risk, worst case behavior of others should not be the default for the motion plan of an automated vehicle. Rather, with a safe reaction to such worst case behavior always in reserve the intended trajectory should be comfortable, less conservative and thereby potentially closer to human expectations. Proposal and exchange of these kind of approaches is the first aim of the workshop.
Multimodal Behavior Prediction: For such behavior, sophisticated behavior prediction approaches for other traffic participants are necessary, going beyond constant velocity assumptions. Predictions must be probabilistic and allow for maneuver options for other vehicles. Often, there is not “the right prediction”, but many. The choice is influenced by destinations as much as individual driving behaviors and potentially even the drivers’ mood. Thus, a simple evaluation against a ground truth is not possible. Prediction approaches, including but not limited to machine learning based approaches, as well as proposals for their evaluation, are the second main goal of this workshop.
Comprehensible Automated Driving: For motion planning in highly interactive scenarios alike, a “ground truth” or “best option” may not exist. To be comprehensible and predictable for other road users, a good plan should be a subset of an expected prediction for a vehicle in the same situation. The combination of planning and prediction, including but not limited to their evaluation and benchmarking, is the third aim of the proposed workshop.
Effects of Automation on Traffic: Data-driven predictions can end up being implicitly conditioned on second-order effects. For example, seeing a recording vehicle or no driver in an autonomous car can influence traffic participant’s decisions. Fixed settings in automated functions, such as safe distances, can influence the traffic flow on highways. While this can potentially introduce a distribution shift for prediction algorithms it could be also leveraged to purposefully shape traffic. We invite therefore also approaches investigating these second-order effects, propagating in highly interactive scenarios.
Preliminary Agenda
Title:
WelcomeTitle:
A Review of Reward Functions for Reinforcement Learning in the context of Autonomous DrivingTitle:
The key to proactive traffic interaction: Overcoming sequential integration of prediction and planning – a survey perspectiveTitle:
Interaction-driven marginal and joint trajectory predictionCoffee Break
Title:
TrajFlow: Learning Distributions over Trajectories for Human Behavior PredictionTitle:
Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph AttentionLunch Break
Title:
KI-PMF: Knowledge Integrated Plausible Motion ForecastingTitle:
Anti-bullying Adaptive Cruise Control: a proactive right-of-way protection approachCoffee Break
Title:
Evaluating and Enhancing the Human-like Interaction Features of Autonomous VehiclesTitle:
Occlusion-aware Motion Planning in Uncertain EnvironmentsTitle:
Panel DiscussionTitle:
ConclusionOrganizers
Sascha Hornauer
MINES Paris
Maximilian Naumann
Bosch Center for Artificial Intelligence (BCAI)
Marcel Hallgarten
University of Tübingen / Bosch
Eike Rehder
Robert Bosch GmbH
Jiachen Li
Stanford University
Wei Zhan
University of California at Berkeley
Martin Lauer
Karlsruhe Institute of Technology (KIT)
Masayoshi Tomizuka
University of California at Berkeley
Arnaud de La Fortelle
Heex Technologies
Christoph Stiller
Karlsruhe Institute of Technology (KIT)
Please get in touch with sascha.hornauer@mines-paristech.fr or any of the organizers in case you have any further questions.
Past Editions
At IV2023, the organizers hosted the latest edition of this workshop: https://kit-mrt.github.io/iv2023-workshop/.