A 36 million SEK funding grant from the Swedish Knowledge Foundation in combination with industry contributions will allow researchers from two successful robotics fields at Örebro University to join forces to create a new research profile named Semantic Robots. In addition to providing full-time employment for seven to eight researchers, the funding will facilitate the appointment of a number of visiting scholars, postdoctoral researchers and doctoral students for various lengths of time.
– This gives us the opportunity and breathing space to tackle novel research questions in a whole new way, says Dimiter Driankov, professor of computer science and director of AASS, Centre for Applied Autonomous Sensor Systems.
The new research profile Semantic Robots is being set up to integrate and develop the competencies found on the one hand within artificial intelligence (AI) and the Cognitive Robotic Systems Lab (CRS), and on the other hand within autonomous navigation and sensor-based perception and the Mobile Robotics and Olfaction Lab. Within CRS, research is conducted into robots that are able to "think" for themselves when planning and executing actions. Within Mobile Robotics and Olfaction, the focus is on robots that are able to perceive their environment by means of sensors and that have an ability to move in such a way that they can autonomously navigate in different environments and handle different types of objects.
– The idea is that semantic robots will combine competencies from both fields. A semantic robot should be able to create a task-related model of its environment with different human-like levels of abstraction which are all based on data acquired by sensors. It must also be able to use the model and its different abstractions of the environment to autonomously plan and carry out the task it has been charged with, says Dimiter Driankov while showing an animation of a truck navigating and handling goods in a factory environment. The truck receives a vast amount of data about the incline of the floor, various obstacles to be negotiated, suitable places for loading and unloading goods and so on. It also needs to know that in order to go to another floor of the building, it needs to take the cargo lift and it needs to react safely if humans or other things unexpectedly get in its way.
– In short, the robot must describe the world in terms that have a meaning for humans, in this case robot programmers and operators, co-workers etc., and then produce a plan of action in order to complete its mission, says Dimiter Driankov, who together with his colleagues has been working on the application to the Knowledge Foundation for a little over a year.
Their efforts have entailed discussions with the businesses that have also invested in the project. The Knowledge Foundation grant is for a six-year period and for the first three years, a total of 15 million SEK worth of contributions have been pledged by Örebro University's industry partners. These include Saab Dynamics (defence industry), Volvo CE (loaders), Atlas Copco Rock Drills (mining equipment), Husqvarna (lawn mowing equipment), Kollmorgen (control systems for automated material handling in warehouses and factories), Optronic (combines optics and electronics), Cnet (links sensors and robots to the Internet), and Hothouse (sensor design).
– We provide the research questions and then there have been discussions with our industry partners in terms of how they can profit by the results, that is, if our ideas can solve their problems.
The Knowledge Foundation was established in the 1990s. Part of its mandate is to support research at Sweden's new universities in collaboration with industry and commerce and by promoting the use of IT.
Text: Lars Westberg
Translation: Charlotta Hambre-Knight
Photo: Tomas Jansohn