Theses in Robotics

Projects in Advanced Robotics

The main objective of the follwing projects is to give students experience in working with advanced robotics tehcnology. Our group is active in several R&D projects involving human-robot collaboration, intuitive teleoperation of robots, and autonomous navigation of unmanned mobile platforms. Our main software platforms are Robot Operating System (ROS) for developing software for advanced robot systems and Gazebo for running realistic robotic simulations.

For further information, contact Karl Kruusamäe

The following is not an exhaustive list of all available thesis/research topics.

KUKA youBot

Development of demonstrative and promotional applications for KUKA youBot

The goal of this project is to develop promotional use cases for KUKA youBot, that demonstrate the capabilities of modern robotics and inspire people to get involved with it. The list of possible robotic demos include:

• using 3D vision for human and/or environment detection,
• interactive navigation,
• autonomous path planning,
• different pick-and-place applications,
• and human-robot collaboration.

Universal Robots UR5

Development of demonstrative and promotional applications for Universal Robots UR5

Sample demonstrations include:

• autonomous pick-and-place,
• load-assistance for human-robot collaboration,
• packaging,
• physical compliance during human-robot interaction,
• tracing objects surface during scanning,
• robotic kitting,
• grinding of non-flat surfaces.

ROS support and educational materials for open-source mobile robot

The goal of the project is to develop Robot Operating System (ROS) wrapper functions for drivers of an open-source mobile robot platform, that has been successfully used in Robotex competitions. Additionally, educational materials must be developed to integrate the robot platform into ROS ecosystem. The outcome of this work will give a lot of educational uses and rapid prototyping opportunities for the platform.

Detecting features of urban and off-road surroundings

Accurate navigation of self-driving unmanned robotic platforms requires identification of traversable terrain. A combined analysis of point-cloud data with RGB information of the robot's environment can help autonomous systems make correct decisions. The goal of this work is to develop algorithms for terrain classification.

Robotic simulations (in Gazebo)

1) Developing large area simulation worlds for mobile robotics. In order to develop robot navigation algorithms, it is more time- and cost-efficient to test robot behavior in a wide range of realistically simulated worlds. These simulated worlds include both indoor and outdoor environments. This work focuses on designing robot simulation environments using an open-source platform Gazebo.
2) Humans in Gazebo. Integrating walking and gesturing humans to Gazebo.
3) Tracked Robots in Gazebo. Creating and testing tracked robotis in Gaxebo and testing different track configurations.

Follow-the-leader robotic demo

Detecting 2 hands with Leap Motion Controller

The idea is to create a robotic demonstration where a mobile robot is using Kinect or similar depth-camera for identifying a person and then starts following that person. The project will be implemented using Robot Operating System (ROS) on either KUKA youbot or similar mobile robot platform.

Detecting hand signals for intuitive human-robot interface

This project involves creating ROS libraries for using either a Leap Motion Controller or an RGB-D camera to detect most common human hand signals (e.g., thumbs up, thumbs down, all clear, pointing into distance, inviting).

Virtual reality user interface (VRUI) for intuitive teleoperation system

Adding virtual reality capability to a gesture- and natural-language-based robot teleoperation system.

Kruusamäe et al. (2016) High-precision telerobot with human-centered variable perspective and scalable gestural interface

Health monitor for intuitive telerobot

Intelligent status and error handling for an intuitive telerobotic system.

Dynamic stitching for achieveing 360° FOV

Automated image stitching of images from multiple camera sources for achieveing 360° field-of-view during mobile telerobotic inspection of remote areas.

3D scanning of industrial objects

Using laser sensors and cameras to create accurate models of inustrial producst for quality control or further processing.

Modeling humans for human-robot interaction

Using cameras and other human sensors to digitally representing and modelling humans. Physical models of human kinematics and dynamics. Higher level-models for recognizing human intent.

ROS & Kinect & Skeleton-Markers Package