Modelling behavior and interaction of road users in transportation systems
Title | Modelling behavior and interaction of road users in transportation systems |
---|---|
Summary | Modelling behavior and interaction of road users in transportation systems |
Keywords | Behavior modeling, agent interaction, machine learning, segmentation, object identification |
TimeFrame | Oct 2019 to June 2020, with possible extension to Sep 2020 |
References | |
Prerequisites | Programming (any of C++, Python, Matlab) |
Author | |
Supervisor | Björn Åstrand, Cristofer Englund |
Level | Master |
Status | Open |
Building a transportation system for everybody requires understanding of the behavior of the different users. This thesis will develop technology to model interactions between different road users in the transportation system. The ultimate use of the models is to enable programming of automated vehicles to perform e.g. let pedestrians cross safely in front of the vehicle, cooperative platoon merge, or automatically negotiate free-of-way in intersections. We have collected data using camera-based sensors that also includes trajectories that can be used to predict future behavior for e.g. action and intention prediction, both from a single user perspective as well as in interaction between two or more road users.
Data: Today data is available along with trajectories of different road users, including, long, lat, speed, time. Some video data is also available.
Research questions: The following research questions will be addresses in the project.
(i) How can semantics (e.g. vehicle type, vehicle size, vehicles brand) from data be utilized to improve interaction and behavior models and how to extract semantics from video data. (ii) How does interaction affect the behavior in traffic? (iii) How can we model behavior with different number of entities involved in the interaction?