Modelling behavior and interaction of road users in transportation systems

2019-09-30T13:04:15Z

BjornA: Created page with "{{StudentProjectTemplate |Summary=Modelling behavior and interaction of road users in transportation systems |Keywords=Behavior modeling, agent interaction, machine learning, ..."

{{StudentProjectTemplate
|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
|Prerequisites=Programming (any of C++, Python, Matlab)
|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?

Segmentation and object identification in warehouse environments using machine learning

2019-09-30T11:45:31Z

BjornA: Created page with "{{StudentProjectTemplate |Summary=Segmentation and object identification in warehouse environments using machine learning |Keywords=Vision, lidar, machine learning, segmentati..."

{{StudentProjectTemplate
|Summary=Segmentation and object identification in warehouse environments using machine learning
|Keywords=Vision, lidar, machine learning, segmentation, object identification
|TimeFrame=Oct 2019 to June 2020, with possible extension to Sep 2020
|Prerequisites=Programming (any of C++, Python, Matlab)
|Supervisor=Björn Åstrand, Naveed Muhammad
|Level=Master
|Status=Open
}}
Context and overview: This master thesis falls in the context of autonomous mobile robots (such as forklift trucks, industrial cleaning robots etc.) that operate in warehouse or factory kind of environments. An autonomous robot needs to perceive its environment and detect and identify objects and agents around it, in order to achieve any given goal (e.g. transporting an object from point A to B). This project focuses on perceiving robot environment using vision and lidar sensing modalities, and then using vision modality (for instance acquired using a camera or Kinect module) for annotating range data (for instance acquired using a time-of-flight camera or a lidar), which will in turn be used for tasks of scene segmentation and object identification.

Data: Datasets, in the form of ROS bag files, acquired in a warehouse environment (including vision and range data) is available to be used in the project. There might be possibilities for more data collection.

Research questions: The following research questions will be addresses in the project.

(i) Can state-of-the-art machine learning algorithms for object identification and scene segmentation based on vision sensing, that work in outdoor environments, be employed for indoor warehouse-like environments using transfer learning.
(ii) Can vision-based-algorithm-generated labels be used for annotation of objects lidar data in warehouse-like settings?
(iii) How can machine learning be used for the tasks of segmentation and object identification in range data in warehouse-like environments.

ISLAB/CAISR - User contributions [en]

Modelling behavior and interaction of road users in transportation systems

Segmentation and object identification in warehouse environments using machine learning