PHD STUDENT IN SEMANTIC SLAM

28 May 2019

Get in touch!

Interested?

Please use the online application tool to submit your application and include: (i) an academic CV with photo, (ii) a pdf of your diplomas and transcript of course work and grades, (iii) statement of research interests and career goals (max. 2 pages), (iv) sample of technical writing (publication or thesis), (v) contact details of at least two referees.

NOTE:  the position might be filled in earlier if an excellent candidate is found.

For more information, send an e-mail to rob.hr@kuleuven.be

You can apply for this job no later than July 31, 2019 via the online application tool
KU Leuven seeks to foster an environment where all talents can flourish, regardless of gender, age, cultural background, nationality or impairments. If you have any questions relating to accessibility or support, please contact us at diversiteit.HR@kuleuven.be.

Apply before 31 July 2019

You will be part of the Robotics Research Group at the Department of Mechanical Engineering, Division of Production engineering, Machine design and Automation (PMA).

The group has pioneered robotics research in Europe since the mid-1970s and was among the first to develop active force feedback for assembly operations. Already in 1980 it developed learning insertion algorithms based on stochastic automata. It has covered virtually all aspects of sensor-based robotics, from the high-level task specification down to low-level sensor-based control, and applied the research results in a variety of industrial applications. In the last decade the group shifted its attention towards service robots (behaviour-based mobile manipulation, shared control, learning control), medical robotics (natural interfaces, haptic bilateral control), industrial robot assistants, and active sensing. PMA has created several spin-off companies that are active in robotics-related activities, has initiated several free and open-source software projects in robotics (Orocos, KDL, iTaSC, eTaSL, …), and has participated in a large number of EU projects in robotics, mostly oriented towards control and software development, with a focus on model-driven engineering techniques. More information is available through the link below.

Website unit

Project

The selected candidate will be involved in the HYSLAM project, a four-year strategic research project. The project focuses on adding semantics to SLAM in order to cope with dynamic environments and to improve reliability to a level ready for industrial uptake. The project will achieve this goal through developing mechanisms that continuously update maps and by making the navigation more robust to changes in the environment. To this end, semantic information will be included in the map representation of the environment, which can then be used to decide which objects in the environment are likely to change and which ones are not. The developed algorithms will be validated on two use cases: one use case in which a mobile robot navigates in an industrial indoor environment, and one use case in which a drone flies in an outdoor environment. For both use cases, a simulation framework and an experimental platform will be developed.

For this vacancy, the selected candidate will focus on the models and underlying data structures for the semantic maps as well as the tooling to efficiently work with them. This includes working on graph-based databases and algorithms to represent domain-specific knowledge about the robots, their sensors, the environment, the task, and relations between them. The use cases of the project are defining the scope for these domain-specific models. The candidate will then develop tooling that supports project partners but also robots in creating, modifying, and querying knowledge in these semantic world models. Since such queries will require the execution of algorithms on the graph structures, the final task of the candidate is to find efficient algorithms and to deploy them in the developed infrastructure, e.g., in the form of microservices in a database.

Profile

A successful candidate has obtained a MSc degree in engineering related to Robotics or Computer Science, and has a background and interest to contribute to

  • using semantic knowledge to improve the reliability of SLAM, and
  • working on complex graph structures to connect knowledge about the task, the robot(s), and their environment into a semantic world model, and
  • producing tooling that help others to create, modify, and query such semantic world models, and
  • integrating such models into the applications targeted within the project by creating domain specific models and their relations for sensors, robots, and the environments.

Software development will be part of your core research. The following elements will be considered in the evaluation:

  • proficiency, in (or willingness to learn) different general purposes languages ( C/C++, Lua, Python, JavaScript, etc.)
  • experience with existing database frameworks (with preference for NO SQL and graph-based databases)
  • experience with SLAM and/or semantic maps
  • experience with writing domain-specific languages is a plus
  • experience with mapping formats and GIS tools (preferably in the Open Street Map ecosystem) is a plus
  • experience with existing robotics middleware (Orocos, ROS, …) is a plus
  • contributions to free and open source software projects (also beyond the topic of the project) are a plus. If so, please list them clearly in your application or send us your portfolio

In your motivation letter or extended CV description, please consider to mention your previous experiences and skills which may help to make relevant contributions to the project.

The selected candidate is furthermore expected to:

  • have a very good knowledge of English (spoken and written)
  • be able to work independently, accurately and methodically
  • be a team player
  • present research findings at national and international conferences
  • publish research findings in international journals

Hands-on experience with databases, robot platforms, or sensor systems (cameras, Lidar,...) are a plus.

Offer

The successful candidate will receive:

  • a fully funded doctoral scholarship for one year, renewable up to four years
  • multiple benefits (health insurance, access to university infrastructure and sports facilities, etc.)
  • the opportunity to participate in research collaborations and international conferences

A start date in the course of 2019 is to be agreed upon.