Dela med andra

Master thesis: Artificial intelligence and dashboard development for intelligent autonomous robots

Publicerad 2017-06-19

Om uppdragsgivaren
Ericsson is a world-leading provider of telecommunications equipment and services to mobile and fixed network operators. Over 1,000 networks in more than 180 countries use Ericsson equipment, and more than 40 percent of the world´s mobile traffic passes through Ericsson networks. Using innovation to empower people, business and society, Ericsson is working towards the Networked Society: a world connected in real time that will open up opportunities to create freedom, transform society and drive solutions to some of our planet’s greatest challenges.
We are truly a global company, operating across borders in over 180 countries, offering a diverse, performance-driven culture and an innovative and engaging environment. As an Ericsson employee, you will have freedom to think big and the support to turn ideas into achievements. Continuous learning and growth opportunities allow you to acquire the knowledge and skills necessary to progress and reach your career goals. We invite you to join our team.

Beskrivning av examensarbetet
Do you want to work with artificial intelligence architectures, autonomous robots and develop data visualization dashboard to support developers, users and other stakeholders?

Today, complex logistics operations include different levels of communication and interactions. This study explores the requirements of these operations and conceptualizes important key performance indicators, stakeholders and different data visualizations to support the stakeholders to understand interactions between entities easier and faster.
To illustrate complex logistics operations we have identified three different levels: supply chain level, automated warehouse level and intelligent agent level. For each level, important stakeholders and performance indicators are determined.
Two Msc. Thesis students will be chosen to conduct related but different thesis work. The study aims to focus on automated warehouse level and extend the earlier framework study by developing existing problem specifications further for planning problem solution and data generation, developing data visualizations about robot’s specifications and behaviors.

Project description
This exploratory study aims to develop plan for the goals of the robots among in addition to data collection methods and data visualizations. Students will conduct literature review and formal laboratory user studies to assess the usability, understandability, intuitivity of the developed dashboard.

Some research questions/problems related with the study are:
1 Artificial Intelligence Student
• How can one describe the knowledge about robots and their behavior?
o Study different ontologies for warehouse and robot domain, and find/extend/develop one suitable for the project.
• Study state of the art behavioral modelling languages such as Planning Domain Definition Language PDDL language, state charts, etc..
• Identify tools that use these modeling languages as input for deriving system behavior e.g. for planning PDDL based planners can be used
• Extend the current behavior model with more complex behavior with respect to time, energy, collaboration for interoperability, multi-agent systems, multi-core planners etc.
• How this output data from the selected tools e.g. planners can be transformed to a syntax e.g. JSON, which can be easily exchanged with other tools or systems?
o Work with the Data Visualization Student to define the most applicable way of sharing data between the tools to generate visualization
2 Data Visualizations Student
• What are the possible data visualization techniques to represent the information about the robots’ specifications and their behaviors?
o Study different visualization techniques and test the applicability of relevant techniques to represent warehouse and robot information. Develop the dashboard to visualize information about robot actions, interactions and specifications.
• What are the existing methods/methodologies and important performance indicators to assess the developed dashboard tool?
• How successful is the dashboard to aid stakeholders in their decision making activities by using formal laboratory user studies?
o Design and conduct a user experience research.

The framework of this study already exists and students will have access to the existing information and knowledge.

The final deliverable is a pre-build executable on at least a desktop device, tablet, and mobile. Everything should be ready for testing for us and the deliverable needs to include the source code as well as and a description how to set it up and build it on our own. You will of course be accredited by name for you contribution.

Technologies you can/will use
PDDL, RDF, XML, JavaScript, HTML5, SVG, C++, Objective-C
If you would like to use other technologies then we can discuss that. When using additional libraries, be aware of how they are licensed, consider the project to be closed source.

Thesis Cycle
The thesis will preferably start in mid September 2017 towards a graduation in February 2018.

Last Application Date
Please apply for the thesis no later than 2017-08-15, the selection process is on-going. As soon as suitable candidates are identified the thesis will be assigned.

Contact information
• Company supervisors: Didem Gürdür,, and Aneta Vulgarakis Feljan

Aneta Vulgarakis Feljan




Sista ansökningdag

Bookmark and Share