Topics of Interest

The ambition of this half-day workshop is to form a platform for exchanging ideas and linking the scientific community working on the application of naturalistic road user trajectory datasets. This workshop will provide an opportunity to discuss needs and possible applications of such datasets.
To this end, we welcome contributions with a strong focus on (but not limited to) the following topics:

  • Naturalistic Road User Data
  • Data-Driven Safety Validation
  • Data-Driven Scenario Extraction
  • Evaluation of Naturalistic Driving Data for Traffic Models
  • Road User Agents for Simulation
  • Driver Models
  • Social behavior and interactions, modeling and quantification of social factors
  • Prediction for various kinds of traffic participants
  • Deep generative models
  • Cooperative Behavior Planning
  • Impact Assessment of Automated Driving
  • Accident Research

Aim and Scope

[Image: InD]

Today, automated vehicles already rely heavily on data-driven methods and the relevance of these methods will continue to grow. This leads to an ever-increasing demand for appropriate data. In terms of training data for environment perception algorithms, there already exist many public datasets, such as e.g. KITTI, Cityscapes, Waymo Open, Lyft Level 5 Dataset, etc. The industry has already established processes to generate such data in large amounts. In contrast, the data demand is still not sufficiently met for many other automated driving tasks such as e.g. Safety Validation, Prediction Models, Driver Models, Simulation Agents and Cooperative Behavior Planning, where there is a need for naturalistic road user trajectory dataset.

Therefore, ika and fka have released the highway drone dataset (highD) and intersection drone dataset (inD), which are large scale naturalistic road user trajectory datasets created using camera-equipped drones. Although these datasets are already fostering research a lot, it is expected that many more road user trajectory datasets from other locations and traffic scenarios are needed in future. For this purpose, a panel discussion will be held in the workshop to investigate the current and further need for road user trajectory.

Furthermore, possible applications of road user trajectory datasets shall be presented by invited speakers from industry and the authors of the accepted workshop papers. Those applications of the datasets do not only allow insight into the current state-of-the-art but also the identification of current limitations.

The field of road user prediction is one of the most important research topics in the field of automated driving working on trajectory datasets. Thus, the workshop organizers will host a challenge (leaderboard) for road user prediction on each of their public datasets highD and inD, where researchers shall compete with each other on new methods for road user prediction on the current state-of-the-art datasets. The challenges will be opened quickly after acceptance leaving the competitors enough time to include results of the challenge in their papers. Participants of the prediction challenges are expected to submit their methods as regular or workshop papers of IEEE IV 2020.

Call for Papers – Dates & Submission

Prospective authors are invited to submit contributions reporting on their current research and ideas that motivate discussion during the workshop. An International Program Committee will analyze each paper according to quality of presentation, relevance and potential contribution.

Accepted papers will be included in the conference proceedings as workshop papers and will be indexed in the IEEE Xplore Digital Library. Authors must follow the IEEE Conference format in the preparation of their manuscripts of maximum six pages in standard IEEE double column PDF format and submit them through the conference submission system for peer-review by the International Program Committee. Manuscripts will be submitted selecting the code number for the workshop on “Ensuring and Validating Safety for Automated Vehicles”.

All accepted papers will imply that at least one of the co-authors attends the workshop to present the work. Authors will be given a certain time to orally present their papers and discussion will be actively motivated among attendees. Further information with regard to the submission process can be found on the conference website. Go directly to the submission site.

Important Dates

March 14, 2020
Submission deadline (firm deadline, no extension)
April 18, 2020
Notification of acceptance
May 8, 2020
Camera ready version due
October 20, 2020

Workshop Schedule: October 20, 2020

Start timeEnd timeTopic
13:00 13:10 Workshop Opening
13:10 13:40 Invitited Talk by Felix Fahrenkrog (BMW)
13:40 14:10 Regular Paper Presentation: Scenario-Based Threat Metric Evaluation Based on the Highd Dataset
14:10 14:40 Regular Paper Presentation: Analysis of Experimental Data on Dynamics and Behavior of E-Scooter Riders and Applications to the Impact of Automated Driving Functions on Urban Road Safety
14:40 15:00 Presentation: Highly accurate traffic data from aerial perspective
15:00 15:30 Invitited Talk by Florent Garnier-Follet (TME)
15:30 16:00 Discussion: Most urgently needed datasets
16:00 16:30 Invitited Talk tbd
16:30 17:00 Presentation: Predition challenges and Summary


[Photo: Julian Bock]

Julian Bock, M.Sc. fka GmbH
Julian Bock has completed his Master studies in Computational Engineering Science at RWTH Aachen University in 2014. After his studies, he started as Scientific Engineer and PhD student at the Institute for Automotive Engineering (ika) at RWTH Aachen University. There, he is working on data-driven safety validation, pedestrian prediction and measurement of naturalistic road user trajectories using drones, which has led to the creation of the inD and highD dataset. Since May 2019, he is manager artificial intelligence. In January 2020, he changed to fka GmbH, again as manager artificial intelligence. There, he is responsible for levelXdata and projects on data-driven safety validation.

[Photo: Adrian Zlocki]

Dr. Adrian Zlocki, fka GmbH
Dr. Adrian Zlocki studied automotive engineering at the RWTH -Aachen University. Since 2004 he has been employed as a Scientific Engineer and PhD student at the ADAS department of the Institute for Automotive Engineering (ika). Between 2007 and 2010 he led a research group in the field of ADAS development and assessment at ika. He is currently head of fka’s Automated Driving department. He is active in several research activities such as L3Pilot (EU), VVMethoden (Germany), SAE/DIN and HEADSTART (EU).

[Photo: Robert Krajewski]

Robert Krajewski, M.Sc., Institute for Automotive Engineering - RWTH Aachen University
Robert Krajewski completed his Master studies in Electrical Engineering with a major in Computer Engineering at RWTH Aachen University in 2015. As a Scientific Engineer at the Institute for Automotive Engineering (ika), within the scope of his doctoral thesis, he focusses on the efficient generation of the trajectory data required for the data-driven safety validation of automated vehicles. He is one of the creators of the inD and highD dataset.

[Photo: Lutz Eckstein]

Univ.-Prof. Dr.-Ing. Lutz Eckstein, Institute for Automotive Engineering - RWTH Aachen University
Prof. Lutz Eckstein is the director and chair of the Institute for Automotive Engineering (ika) at RWTH Aachen University. He brings many years of professional experience in the automotive industry. Following completion of his studies in mechanical engineering, including a doctoral degree from the University of Stuttgart, Eckstein worked for ten years in research and development at Daimler AG, followed by five years in a management position at BMW Group in the electrical/electronic area. Since 2010 he is heading the Institute of Automotive Engineering at RWTH Aachen University, the key current research areas of which notably include topics such as automated driving, electromobility, innovative steering concepts and lightweight design. Among his many professional activities, Prof. Eckstein is inventor of more than 80 German and international patents.